agentleFS
t1mericksont1merickson/skills/claude/SKILL.md

claude

Skill1 starsChanged 2 months agoMITView on GitHub

Explicit-only: consult or delegate to Claude from Codex for a bounded second opinion, investigation, implementation lane, synthesis, or cross-vendor handoff. Use only when the user asks to invoke Claude or names this skill. Do not use for ordinary independent reasoning, routine repository work, or an incidental mention of Claude.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use compare-screenshots, implement-spec-with-codex and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • transitive-bullshitSkill

    compare-screenshots

    Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.

    Also in 5 projects that use this

  • dzhngSkill

    implement-spec-with-codex

    Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.

    Also in 4 projects that use this

  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 4 projects that use this

  • wolverin0Skill

    audit-decisions

    Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.

    Also in 4 projects that use this

  • bergsideSkill

    ant

    Structured, enterprise-focused design system emphasizing clarity, consistency, and efficiency for data-dense web applications.

    Also in 3 projects that use this

  • bergsideSkill

    artistic

    High-contrast, expressive style with creative typography and bold color choices for visually striking interfaces.

    Also in 3 projects that use this

  • +4 more from dzhng
  • +2 more from bergside

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Claude when an independent context, Claude-native capability, or genuine ownership of a bounded lane improves the outcome.

    line 8
  2. Distinctive:

    Consult: read-only judgment, critique, or product/technical opinion.

    line 12
  3. Distinctive:

    Investigate: read-only evidence gathering with a supported conclusion.

    line 13
  4. Distinctive:

    Read references/prompting.md.

    line 27
  5. Very specific:

    Read references/cli.md and verify current flags with claude --help.

    line 39
  6. Distinctive:

    Use Claude's read-only/plan and tool allowlist controls for consultation.

    line 41
  7. Distinctive:

    Use its normal edit permission mode only when implementation was delegated.

    line 42
  8. Distinctive:

    Never use permission-bypass flags as a shortcut.

    line 44
  9. Distinctive:

    Start fresh for independence.

    line 45

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Claude

Use Claude when an independent context, Claude-native capability, or genuine ownership of a bounded lane improves the outcome. Do not delegate for ceremony or to avoid making a local decision. The calling task remains responsible for verifying any result it presents as complete.

Choose the relationship

  • Consult: read-only judgment, critique, or product/technical opinion.
  • Investigate: read-only evidence gathering with a supported conclusion.
  • Delegate: a bounded outcome with explicit edit/test authority.
  • Handoff: a continuing lane transferred through repository state and a durable handoff.

One sharp answer usually needs consultation, not a new workstream. Keep one writer per checkout. Hand off only when work will genuinely continue in Claude's context.

Select model and effort deliberately

Probe the installed CLI and account rather than assuming an alias exists. Model names, effort levels, pricing, and availability change. Apply the local preferences in references/routing.md only after confirming they are supported.

Model choice reflects baseline judgment and desired independence. Effort reflects the obscurity and complexity of this task. Large input is not the same as hard reasoning, and increased effort does not repair an underspecified brief.

Brief the outcome

Read references/prompting.md. Include:

  1. one outcome or decision;
  2. relevant evidence and settled decisions;
  3. scope and authority boundaries;
  4. observable completion criteria;
  5. required return evidence and format.

Point to repository files rather than pasting an entire conversation. Invite disagreement when the premise is uncertain.

Dispatch within Claude's conventions

Read references/cli.md and verify current flags with claude --help.

  • Use Claude's read-only/plan and tool allowlist controls for consultation.
  • Use its normal edit permission mode only when implementation was delegated.
  • Respect project CLAUDE.md, settings, hooks, agents, and worktree conventions.
  • Never use permission-bypass flags as a shortcut.
  • Start fresh for independence; resume when shared context is the point.

Verify the return

Inspect actual files and diffs, reproduce material checks, and distinguish evidence from persuasive prose. Repair a small miss locally or send one focused follow-up. If steering repeats without progress, take the lane back or reframe it.

For continuing work, use references/handoff.md. Repository state and explicit decisions are the shared truth.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.