agentleFS
elxecutorelxecutor/skills/claude/SKILL.md

claude

Skill3 starsChanged yesterdayMITView on GitHub

Access the user's Claude.ai conversations through claude-cli: list, read, create, rename, delete, and continue chats. Use for @claude requests, Claude conversation management, or work that must be performed in Claude.ai.

37 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

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

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 1

    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:

    Never invent conversation content — only report what the tool returns.

    line 13
  2. Very specific:

    If output says cookie expired/missing, stop and tell the user to run claude-cli --update-cookie.

    line 73

“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 via claude-cli

Route every Claude.ai interaction through ~/.agents/skills/claude/claude-cli via bash. Cookie auto-loads from ~/.agents/skills/claude/claude-cookie. The bundled CLI checks its base dependencies (bash, curl, python3) and keeps its cookie in this folder. A distributed copy must exclude claude-cookie; the user authenticates it locally with claude-cli --update-cookie. Never invent conversation content — only report what the tool returns.

Commands

  • List conversations: ~/.agents/skills/claude/claude-cli --list
  • Show history: ~/.agents/skills/claude/claude-cli --history -c <conversation-uuid>
  • Send message: ~/.agents/skills/claude/claude-cli -c <conversation-uuid> "message"
  • New conversation: ~/.agents/skills/claude/claude-cli --new "title" (title optional)
  • Rename: ~/.agents/skills/claude/claude-cli --rename -c <conversation-uuid> "new name"
  • Delete: ~/.agents/skills/claude/claude-cli --delete -c <conversation-uuid>

--history prints the full text of every message returned by Claude's history endpoint, without a character cap, and includes non-text content blocks.

Routing

  • list / list conversations → run --list, present each UUID with its name.
  • UUID only → run --history for that UUID, then summarize it.
  • UUID + message → run --history first to load context, then send the message with -c, return the output.
  • Message with no UUID → run --list first so a conversation can be picked; ask the user which one if ambiguous.
  • new chat / new conversation (+ optional title and opening message) → run --new "title", then start the subagent loop below on the fresh UUID. If an opening message was given, send it as the first turn.
  • rename → run --rename -c <uuid> "new name", confirm the new name.
  • delete → only on explicit user request; echo the conversation name from --list first so the target is unambiguous, then run --delete -c <uuid>.

Progressive conversation (subagent loop)

For anything beyond list/history — any question, problem, or review — do not chat inline. Spawn ONE subagent via the task tool (subagent_type: general) and let it carry the back-and-forth to a conclusion:

  1. Resolve the conversation UUID — given, picked from --list, or freshly created with --new for a new chat (ask if ambiguous) — run --history to load context, and build the opening message with workspace context folded in (see below).
  2. Instruct the subagent to loop on that same UUID: send via ~/.agents/skills/claude/claude-cli -c <uuid> "message" (multi-line and quotes are safe — the CLI JSON-encodes the body), then immediately verify with ~/.agents/skills/claude/claude-cli --history -c <uuid>: the new human message AND a fresh assistant reply must appear in the tail before the next turn. If the send printed an error or history shows nothing new, stop and surface the error instead of looping blindly — then either conclude or follow up, never stop mid-thread with a partial answer.
  3. Each follow-up must progress the thread: answer Claude's questions from the workspace, challenge gaps, demand specifics. No repeated or stalled questions.
  4. Conclude when Claude gives a definitive answer with no open questions, when a blocker appears (auth failure → report claude-cli --update-cookie), or at a turn cap of 8. The subagent returns the conclusion plus a condensed transcript.

Context

The subagent has full workspace access. Every message it sends — opening and follow-ups — folds in whatever is under discussion: the current topic plus the relevant file snippets or diffs (condensed, not whole dumps). Keep each message focused so Claude gets what it needs without noise.

Auth failure

If output says cookie expired/missing, stop and tell the user to run claude-cli --update-cookie.

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.