Skills for Real Engineers. Straight from my .agents directory.
closed-loop
Agent skill fromhuytieu/COG-second-brain
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.
How to install closed-loop
npx skills add huytieu/COG-second-brain# or add only this skill to Claude Code: copy the folder
skills/closed-loop/
# into
~/.claude/skills/closed-loop/ (all projects)
.claude/skills/closed-loop/ (one project)
1# Closed-loop execute (V-model right arm)23Mechanical verification pipeline. Every verify step emits **evidence rows** tied to acceptance criterion IDs (`AC-n`).45## When to use67The harness is opt-in. Run it when:89- Invoked as `/closed-loop <task>` or `/closed-loop <spec-path>`.10- The user asks for the closed loop, proper verification, or an evidence trail.11- `verification_harness: on` in `00-inbox/MY-PROFILE.md` and this is a build task.12- Another skill that declares a `normal`+ lane reaches its verify step.1314Do **not** run it on a request that did not ask for it. Notes, briefs, research, drafts, and ordinary edits are not harness runs, and a checkpoint ledger on those is pure overhead.1516## Phase 0 — Lane + run folder1718```bash19bash .claude/lib/lane-classify.sh explain "<task>"20bash .claude/lib/checkpoint.sh init 04-projects/harness/runs/<YYYY-MM-DD-HHmm>21```2223| Lane | Checkpoints |24|---|---|25| `tiny` | CP-3 → CP-5 (if mutating) |26| `normal` | CP-1 → CP-2 → CP-3 → CP-3v → CP-5 |27| `full` | + CP-4 + claim-verifier + CP-6 |28| `bug` | root-cause ledger (CP-0) before CP-3 |2930Record: `checkpoint.sh record <run-dir> CP-0 PASS|SKIP "<lane>"`3132## Phase 1 — CP-1 Spec (acceptance criteria)3334If spec exists, use its `## Acceptance criteria` + traceability matrix. Else write:3536`04-projects/harness/runs/<id>/criteria.md` using `references/spec-template.md` (criteria + matrix sections only).3738Each criterion: **falsifiable** + `AC-n` ID + verify method.39…
Excerpt shown under the repository's MIT license.
More skills in COG-second-brain
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
