Install
$ agentstack add skill-ccomkhj-skills-summarize ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
summarize
Phase 4 of pair-goal. Runs when iteration ends — either the goal cleared (condition met) or the round cap was reached. Produces .pairgoal/SUMMARY.md and a concise chat recap. This is also the source for the PR body in clean-up.
What to report
Read STATE.md (round log), every R.md, and the current main tree. Then write .pairgoal/SUMMARY.md (template in [../pair-goal/reference/file-formats.md](../pair-goal/reference/file-formats.md)) covering:
- Goal vs achieved — restate the
/goalcondition and whether it was met. If partial (cap hit), give the final check numbers and how far short. - Per round — who won (claude / codex / neither) and the one-line reason. This shows where the value came from and whether one racer dominated.
- Net change kept — the cumulative diff against the base commit (
git diff ..HEAD --stat), and the before→after on the success signal. - Correctness — which checks pass on the final main tree right now. Re-run the stated check and put its output in the summary; don't claim "passing" from memory.
- Follow-ups / left undone — anything out of scope, deferred, or newly surfaced.
Verify before you claim
Before writing "goal achieved", actually run the stated check on the main tree and paste the output. Evidence before assertion — a summary that overstates the result is worse than one that honestly reports a partial win.
Hand off
Show the user the recap (goal-vs-achieved + net diff stat + correctness line), then advance PHASE: cleanup and hand to clean-up:
> Goal met (or: cap reached, partial). Summary in .pairgoal/SUMMARY.md. > Next: clean-up to commit on a branch and open a PR — I'll show you the PR > body and branch first.
Leave the worktrees alone — clean-up tears them down as part of finishing.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ccomkhj
- Source: ccomkhj/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.