You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit e8c7242
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: .agents/skills/build-from-issue/SKILL.md
+29-14Lines changed: 29 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: build-from-issue
3
3
description: Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the `agent:*` workflow labels. Includes tests, documentation updates, and PR creation. Trigger keywords - build from issue, implement issue, work on issue, build issue, start issue.
4
+
metadata:
5
+
internal: true
4
6
---
5
7
6
8
# Build From Issue
@@ -25,7 +27,9 @@ A direct request authorizes only what it says. A request to review or plan does
25
27
26
28
The two request labels remain human-only queue controls. Under **no circumstances** should this skill or any agent apply them, ask to apply them, or suggest automating their application.
27
29
28
-
Do not refuse a direct user request merely because its request label is absent. If direct work begins on an issue that was not already in the label-driven workflow, do not introduce `agent:in-progress` or `agent:pr-opened` solely for that invocation. If a matching request label is present, preserve the existing label transitions so unattended agents can track the workflow.
30
+
In direct mode, issue lifecycle and `agent:*` workflow labels are advisory rather than gates. Inspect the labels and warn the user about each expected label that is missing or any lifecycle label that indicates the normal workflow is incomplete, then continue with the requested phase. Do not ask the user to fix the labels first. A direct request does not change the issue's disposition or make the labels accurate; it only authorizes the requested work.
31
+
32
+
If direct work begins on an issue that was not already in the label-driven workflow, do not introduce `agent:in-progress` or `agent:pr-opened` solely for that invocation. If a matching request label is present, preserve the existing label transitions so unattended agents can track the workflow.
29
33
30
34
## Agent Comment Markers
31
35
@@ -59,11 +63,11 @@ Fetch issue + comments
59
63
├─ topic:security present?
60
64
│ → Route to review-security-issue or fix-security-issue; STOP
61
65
│
62
-
├─ Triage incomplete, awaiting information, or awaiting human disposition?
63
-
│ → Report the blocking state and STOP
66
+
├─ Direct mode + expected lifecycle or agent-workflow labels missing/incomplete?
67
+
│ → Warn which labels are missing or incomplete; continue with the requested phase
64
68
│
65
-
├─ state:accepted and roadmap association both absent?
66
-
│ → Human has not accepted the issue; STOP
69
+
├─ Queue mode + triage incomplete, awaiting information, or awaiting human disposition?
70
+
│ → Report the blocking state and STOP
67
71
│
68
72
├─ No plan comment and no direct planning request and agent:plan-requested absent?
69
73
│ → No request for agent planning; STOP
@@ -109,13 +113,15 @@ If the issue is closed, report that and stop.
109
113
110
114
If `topic:security` is present, stop. General build agents must not plan or implement security issues. Route planning/review to `review-security-issue` and authorized remediation to `fix-security-issue`.
111
115
112
-
Stop before planning in any of these states:
116
+
In queue mode, stop before planning on `state:triage-needed` or `state:needs-info`, and stop on `state:validated` without roadmap placement. Require `state:accepted` or roadmap placement before queue work proceeds. If no plan exists, require `agent:plan-requested`; require `agent:implementation-requested` before queue-mode implementation.
117
+
118
+
In direct mode, inspect the same expected workflow state but do not stop because a lifecycle or agent-workflow label is absent or incomplete. Before continuing, warn the user with the specific discrepancy, for example:
119
+
120
+
> "Issue #42 is missing `state:accepted` or roadmap placement and `agent:implementation-requested`. Those labels are expected in the queued workflow, but your direct request authorizes implementation, so I am continuing without changing them."
113
121
114
-
-`state:triage-needed`: the issue has not been assessed; use `triage-issue`.
115
-
-`state:needs-info`: triage is waiting for evidence from the reporter.
116
-
-`state:validated` without roadmap placement: triage is complete, but a human has not yet decided whether OpenShell should invest in the work.
122
+
If `state:triage-needed`, `state:needs-info`, or `state:validated` is present, name that state in the warning and explain what it normally means. Continue unless the issue lacks information that is actually necessary to perform the requested work; in that case, report the concrete missing information rather than treating the label itself as the blocker.
117
123
118
-
Next, require a human acceptance signal: either `state:accepted` or placement on the roadmap. The label records acceptance without requiring scheduling; roadmap placement records acceptance and sequencing. If no plan exists, require either a direct user request for planning or the human-applied `agent:plan-requested` label before generating one. Never add or remove `state:accepted`, either human request label, or the `roadmap` label.
124
+
Never add or remove `state:accepted`, either human request label, or the `roadmap` label.
119
125
120
126
## Step 2: Fetch and Classify Comments
121
127
@@ -140,7 +146,7 @@ Using the state machine above, determine what to do based on:
140
146
1. Whether a plan comment exists
141
147
2. Whether there are human comments newer than the last agent comment (plan or conversation)
142
148
3. Whether this is direct mode and which phase the user requested
143
-
4. Which disposition, roadmap, and agent-workflow labels are present (`state:accepted`, `agent:plan-requested`, `agent:plan-ready`, `agent:implementation-requested`, `agent:in-progress`, `agent:pr-opened`, and the `roadmap` label)
149
+
4. Which lifecycle and agent-workflow labels are present (`state:*`, `agent:plan-requested`, `agent:plan-ready`, `agent:implementation-requested`, `agent:in-progress`, and `agent:pr-opened`) and which discrepancies require a direct-mode warning
144
150
145
151
Follow the appropriate branch below.
146
152
@@ -681,7 +687,7 @@ If the `agent:in-progress` label is present, the skill was previously started bu
681
687
User says: "Plan issue #42"
682
688
683
689
1. Fetch issue #42 — title: "Add pagination to dataset list endpoint"
684
-
2.Confirm `state:accepted`with no blocking triage state; the user's direct request authorizes planning even if `agent:plan-requested` is absent
690
+
2.Notice that `state:accepted`and `agent:plan-requested` are absent; warn that the issue does not match the queued workflow, then continue because the user directly requested planning
685
691
3. Fetch comments — no `🏗️ build-plan` marker found
686
692
4. Pass issue to `principal-engineer-reviewer` for analysis
687
693
5. Reviewer produces a plan: feat type, Medium complexity, 3 implementation steps, unit + integration tests needed
@@ -713,7 +719,7 @@ User says: "Check issue #42"
713
719
714
720
User says: "Build issue #42"
715
721
716
-
1. Fetch issue #42 — `state:accepted` is present; the user's direct request authorizes implementation
722
+
1. Fetch issue #42 — `state:accepted` is present but `agent:implementation-requested` is absent; warn about the missing queue label and continue because the user directly requested implementation
717
723
2. Plan exists (Revision 2), complexity: Medium, confidence: High
718
724
3. No conflicting branches or PRs
719
725
4. Create branch `feat/42-add-pagination/jmyers`
@@ -727,6 +733,15 @@ User says: "Build issue #42"
727
733
12. No agent-workflow label transition is needed
728
734
13. Report PR URL and workflow run status to user
729
735
736
+
### Run directly on an issue outside the workflow state machine
737
+
738
+
User says: "Build issue #42"
739
+
740
+
1. Fetch issue #42 — it has `state:triage-needed`; neither `state:accepted` nor `agent:implementation-requested` is present
741
+
2. Warn that triage and acceptance are incomplete and name the missing implementation request label
742
+
3. Continue through planning and implementation because the user directly requested the work
743
+
4. Do not add, remove, or reinterpret lifecycle or agent-workflow labels
744
+
730
745
### Run on issue with existing PR
731
746
732
747
User says: "Build issue #42"
@@ -739,7 +754,7 @@ User says: "Build issue #42"
739
754
740
755
User says: "Build issue #99"
741
756
742
-
1. Fetch issue #99 — `state:accepted` is present; the user's direct request authorizes implementation
757
+
1. Fetch issue #99 — warn about any missing expected workflow labels, then continue because the user directly requested implementation
743
758
2. Plan exists: complexity High, confidence Low, has open questions
744
759
3. Warn user: "Issue #99 is rated High complexity / Low confidence. Proceeding but flagging for your awareness."
Copy file name to clipboardExpand all lines: .agents/skills/build-openshell-mxc-windows/SKILL.md
+7-5Lines changed: 7 additions & 5 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: build-openshell-mxc-windows
3
3
description: Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64. Use when working on Windows compilation, `windows:*` mise tasks, unsupported Windows compute-driver contracts, or Windows build reports. This skill does not implement Docker, Kubernetes, Podman, VM, MXC driver, policy translation, MSI, service, or supervisor runtime support on Windows.
4
+
metadata:
5
+
internal: true
4
6
---
5
7
6
8
# Build OpenShell-MXC for Windows
@@ -231,7 +233,7 @@ crypto dependency builds.
231
233
|`windows:build:arm64`| Release-builds `openshell-gateway.exe` and `openshell.exe` for ARM64. |
232
234
|`windows:test:x64`| Runs native x64 workspace tests with `--no-fail-fast`, excluding unsupported Windows packages as top-level workspace targets. |
233
235
|`windows:test:arm64`| Runs native ARM64 workspace tests with `--no-fail-fast` and the same package exclusions. Rejects non-ARM64 hosts. |
234
-
|`windows:test:unsupported:x64`| Re-runs focused `openshell-server` tests for unsupported Windows driver behavior. |
236
+
|`windows:test:unsupported:x64`| Re-runs focused `openshell-gateway` tests for unsupported Windows driver behavior. |
235
237
|`windows:test:unsupported:arm64`| Re-runs the same focused contracts natively on ARM64. Rejects non-ARM64 hosts. |
236
238
|`windows:artifacts`| Reports size and SHA256 for release artifacts that exist. |
237
239
|`windows:ci`| Runs the full ordered x64-host Windows CI lane, plus ARM64 check/build when not skipped. |
@@ -248,10 +250,10 @@ Windows must continue to reject unsupported compute drivers clearly.
248
250
249
251
| Driver | Windows build behavior | Runtime behavior |
250
252
|---|---|---|
251
-
| Docker | Driver crate excluded; server config contract retained. | Gateway construction returns unsupported. |
252
-
| Kubernetes | Driver crate excluded; server config contract retained. | Gateway construction returns unsupported. |
253
-
| Podman | Driver crate excluded; server config contract retained. | Gateway construction returns unsupported. |
254
-
| VM | Driver crate excluded from workspace validation. | Gateway construction returns unsupported. |
Copy file name to clipboardExpand all lines: .agents/skills/create-github-issue/SKILL.md
+3-1Lines changed: 3 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: create-github-issue
3
3
description: Create GitHub issues using the gh CLI. Use when the user wants to create a new issue, report a bug, request a feature, or create a task in GitHub. Trigger keywords - create issue, new issue, file bug, report bug, feature request, github issue.
4
+
metadata:
5
+
internal: true
4
6
---
5
7
6
8
# Create GitHub Issue
@@ -123,7 +125,7 @@ EOF
123
125
124
126
GitHub built-in issue types (`Bug`, `Feature`, `Task`) should come from the matching issue template when possible, or be set manually afterward. Do not try to emulate them through labels.
125
127
126
-
Creating an issue does not accept it or queue agent work. Agents never apply `state:accepted`, the `roadmap` label, add issues to the roadmap project, or apply `agent:plan-requested` or `agent:implementation-requested`. Community issues proceed through `triage-issue`; a human accepts technically validated work with `state:accepted` or roadmap placement. The request labels queue work for unattended agents; a user may instead direct an agent to a specific issue.
128
+
Creating an issue does not accept it or queue agent work. Agents never apply `state:accepted`, the `roadmap` label, add issues to the roadmap project, or apply `agent:plan-requested` or `agent:implementation-requested`. Community issues proceed through `triage-issue`; a human accepts technically validated work with `state:accepted` or roadmap placement. The request labels queue work for unattended agents. A user may instead direct an agent to a specific issue; the agent warns about missing expected workflow labels and continues with the requested phase without changing them.
Copy file name to clipboardExpand all lines: .agents/skills/create-github-pr/SKILL.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: create-github-pr
3
3
description: Create GitHub pull requests using the gh CLI. Use when the user wants to create a new PR, submit code for review, or open a pull request. Trigger keywords - create PR, pull request, new PR, submit for review, code review.
Copy file name to clipboardExpand all lines: .agents/skills/create-rfc/SKILL.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: create-rfc
3
3
description: Create OpenShell RFC proposals in rfc/ from a design request. Use when the user asks to write, draft, start, create, or update an RFC, Request for Comments, architecture proposal, API proposal, process proposal, or cross-cutting design proposal that should follow the OpenShell RFC process and template.
Copy file name to clipboardExpand all lines: .agents/skills/create-spike/SKILL.md
+4-2Lines changed: 4 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: create-spike
3
3
description: Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to build-from-issue — maps vague ideas to concrete, buildable issues. Trigger keywords - spike, investigate, explore, research issue, technical investigation, create spike, new spike, feasibility, codebase exploration.
4
+
metadata:
5
+
internal: true
4
6
---
5
7
6
8
# Create Spike
@@ -211,7 +213,7 @@ gh issue create \
211
213
- <what tests exist for the affected area today, what patterns should be followed, any test infrastructure gaps>
212
214
213
215
---
214
-
*Created by spike investigation. `state:validated` means the issue is ready for human disposition; `state:needs-info` means specific evidence is still required. A human applies `state:accepted` or places the issue on the roadmap if OpenShell should pursue the work. To queue unattended agent planning, a human applies `agent:plan-requested`; a direct request to an agent does not require that label.*
216
+
*Created by spike investigation. `state:validated` means the issue is ready for human disposition; `state:needs-info` means specific evidence is still required. A human applies `state:accepted` or places the issue on the roadmap if OpenShell should pursue the work. To queue unattended agent planning, a human applies `agent:plan-requested`; on a direct request, the agent warns about missing expected workflow labels and continues without changing them.*
215
217
EOF
216
218
)"
217
219
```
@@ -235,7 +237,7 @@ After creating the issue, report:
235
237
236
238
For `state:validated`:
237
239
238
-
> Review the issue and decide whether OpenShell should pursue it. If yes, apply `state:accepted`, associate it with a roadmap item, or do both. Either action records acceptance; roadmap placement additionally records sequencing. The work may remain human-owned. Apply `agent:plan-requested` to queue planning for an unattended agent, or directly ask an agent to use `build-from-issue`. If no, close it as not planned and record the rationale.
240
+
> Review the issue and decide whether OpenShell should pursue it. If yes, apply `state:accepted`, associate it with a roadmap item, or do both. Either action records acceptance; roadmap placement additionally records sequencing. The work may remain human-owned. Apply `agent:plan-requested` to queue planning for an unattended agent, or directly ask an agent to use `build-from-issue`; on a direct request, the agent warns about missing expected workflow labels and continues without changing them. If no, close it as not planned and record the rationale.
Copy file name to clipboardExpand all lines: .agents/skills/fix-security-issue/SKILL.md
+7-4Lines changed: 7 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,8 @@
1
1
---
2
2
name: fix-security-issue
3
3
description: Implement a fix for a reviewed security issue. Takes a directly requested issue number or scans for issues labeled `topic:security` and `agent:implementation-requested`. Reads the security review from the issue comments and implements the remediation plan. Trigger keywords - fix security issue, remediate security, implement security fix, patch vulnerability.
4
+
metadata:
5
+
internal: true
4
6
---
5
7
6
8
# Fix Security Issue
@@ -11,7 +13,7 @@ Implement a code fix for a security issue that has already been reviewed by the
11
13
12
14
- The `gh` CLI must be authenticated (`gh auth status`)
13
15
- You must be in a git repository with a GitHub remote
14
-
- The issue must have `topic:security`. In unattended scan mode it must also have `agent:implementation-requested`; a direct user request to fix a specific issue does not require that label.
16
+
- The issue must have `topic:security`. In unattended scan mode it must also have `agent:implementation-requested`; for a direct user request, warn if that workflow label is missing and continue without changing it.
15
17
- The issue must have a prior security review comment (posted by `review-security-issue`) with a **Legitimate concern** determination and a remediation plan
16
18
17
19
## Agent Comment Marker
@@ -30,7 +32,7 @@ The user may provide an issue number directly, or ask the agent to find issues t
30
32
31
33
### If an issue number is provided
32
34
33
-
Strip any leading `#` and proceed to Step 2 with that issue ID. The user's explicit fix request authorizes implementation; do not refuse solely because `agent:implementation-requested` is absent.
35
+
Strip any leading `#` and proceed to Step 2 with that issue ID. The user's explicit fix request authorizes implementation. If `agent:implementation-requested` is absent, warn that the expected workflow label is missing and continue without changing it.
34
36
35
37
### If no issue number is provided
36
38
@@ -61,7 +63,7 @@ Check the issue's `labels` array from the response above:
61
63
62
64
If `topic:security` is missing, report that this skill only handles security issues and stop. If queue mode selected an issue without `agent:implementation-requested`, report that it is not ready for unattended pickup and stop.
63
65
64
-
Never apply `agent:implementation-requested` yourself. Its absence does not block a direct user request to fix a specific issue.
66
+
Never apply `agent:implementation-requested` yourself. In direct mode, warn about its absence and continue; the missing label does not block the user's request to fix the specific issue.
65
67
66
68
### Validate the security review
67
69
@@ -307,7 +309,8 @@ User says: "Fix security issue #55"
307
309
1. Fetch issue #55 metadata
308
310
2. Labels are `["topic:security"]` -- missing `agent:implementation-requested`
309
311
3. Confirm that a legitimate security review and remediation plan exist
310
-
4. Proceed because the user's direct request authorizes implementation
312
+
4. Warn that `agent:implementation-requested` is missing from the expected workflow state
313
+
5. Proceed because the user's direct request authorizes implementation; leave the labels unchanged
0 commit comments