agentleFS
Sign inStart free
MorganOnGitHubMorganOnGitHub/tackle/skills/writing-skills/SKILL.md

writing-skills

Skill0 starsChanged 47 days agoMITView on GitHub

Use when creating a new Tackle skill, editing an existing one, or checking that a skill changes agent behavior the way it should

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions 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.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 20 projects that use this

  • kntismSkill

    condition-based-waiting

    Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

    Also in 3 projects that use this

  • aaddrickSkill

    writing-agents

    Use when creating new agents, editing existing agents, or defining specialized subagent roles for the Task tool

    Also in 3 projects that use this

  • frankxaiSkill

    defense-in-depth

    Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

    Also in 3 projects that use this

  • +3 more from Leodorareluctant259

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 180 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    New skill or behavioral change: follow the steps below, including evals.

    line 13
  2. Distinctive:

    Start from observed behavior: Run the scenario without the skill and note what the agent actually does wrong.

    line 17
  3. Distinctive:

    Stay portable: no personal names or in-jokes, no branded paths in user repos, git optional, and tools described by role ("run the tests", …

    line 30

“Common” is measured: kept by at least 6 in 10 of the 180 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

Writing Skills

A skill is reusable judgment: how to approach a kind of task, and when not to. Good skills are short, explain their reasoning, and are tested against real scenarios, including ones where the skill should stay quiet.

Scale it

  • Wording tweak: edit, then re-read the skill as an agent would.
  • New skill or behavioral change: follow the steps below, including evals.

How

  1. Start from observed behavior. Run the scenario without the skill and note what the agent actually does wrong. If nothing goes wrong, you may not need the skill.
  2. Write the frontmatter:
    • name: lowercase-hyphenated, verb-led (testing-first, finishing-work)
    • description: when to use it: triggering situations and symptoms, starting with "Use when…", under 1024 characters. Use the words an agent would have in mind at that moment, such as error text, tool names and symptoms. Don't summarize the steps; agents may follow the summary instead of reading the skill.
  3. Follow the Tackle template so every skill reads alike:
    • Purpose paragraph: what it achieves and why it matters
    • ## Scale it: what to do at each size (trivial / small / substantial, or risk levels)
    • ## How: the steps
    • ## Skip or shorten when: explicit exits
    • ## Done means: the observable finish line
    • ## Next: suggested follow-on skills, never mandated
  4. Write for a capable colleague. Give reasons instead of volume: no ALL CAPS, threats, or "no exceptions". Where a rule really is firm, say why it's firm. Never claim precedence over the user or the harness.
  5. Keep it lean: under 500 words, with detail moved into supporting files in the skill's folder. Put each fact in one place; don't restate the steps as a diagram and a checklist. One complete, realistic example teaches more than several partial ones.
  6. Stay portable: no personal names or in-jokes, no branded paths in user repos, git optional, and tools described by role ("run the tests", "dispatch a subagent") rather than one harness's names.
  7. Add eval scenarios to evals/scenarios.md: at least one where the skill should apply, and one where it should not (usually a trivial task).
  8. Measure against baseline. Compare runs with and without the skill on outcome, turns and tokens. When a run goes wrong, find the wording that allowed it and fix it with a reason. Keep a skill only if it helps.

Skip or shorten when

  • The guidance is project-specific. It belongs in that project's instruction file (CLAUDE.md, AGENTS.md, GEMINI.md), not in Tackle.

Done means

The skill follows the template, stays within budget, and has should-apply and should-not-apply scenarios with baseline results noted.

Next

  • requesting-review for the skill text itself

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.

Check your setup, free