agentleFS
r-jellyr-jelly/chronicle/skills/export-resume/SKILL.md

export-resume

Skill0 starsChanged 4 months agoMITView on GitHub

Export reviewed Chronicle projects and STAR stories into concise Korean or English Markdown resume sections. Use when drafting project experience bullets, assembling a Markdown resume, selecting defensible career claims, or refreshing resume content from the local Chronicle story bank.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a Markdown resume artifact from reviewed evidence.

    line 8
  2. Very specific:

    Read relevant PROJECT.md, OWNERSHIP.md, EVIDENCE.md, and STAR.md files.

    line 20
  3. Very specific:

    Use only reviewed stories or sessions and [confirmed] claims by default.

    line 21
  4. Very specific:

    If the user explicitly wants to include an unresolved claim, show it separately as a draft and require confirmation before it enters the …

    line 23
  5. Distinctive:

    Prefer two or three strong bullets over exhaustive task lists.

    line 51
  6. Distinctive:

    Do not expose private evidence references in the public-facing bullets.

    line 54
  7. Distinctive:

    Before presenting the draft, verify:

    line 58
  8. Distinctive:

    Every bullet maps to a reviewed, confirmed source claim.

    line 60
  9. Distinctive:

    Do not overwrite an existing export without explicit confirmation.

    line 76

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Export Resume

Create a Markdown resume artifact from reviewed evidence. This MVP does not generate DOCX, PDF, LaTeX, or job-specific claims that are absent from Chronicle.

Resolve the Export

Determine:

  • target language, defaulting to the conversation language;
  • selected projects or stories;
  • target role or emphasis, if supplied;
  • destination filename.

Read relevant PROJECT.md, OWNERSHIP.md, EVIDENCE.md, and STAR.md files. Use only reviewed stories or sessions and [confirmed] claims by default.

If the user explicitly wants to include an unresolved claim, show it separately as a draft and require confirmation before it enters the export. Never silently promote [inferred] or [needs-evidence].

Select and Write

Prioritize claims that demonstrate:

  • a meaningful problem and constraint;
  • clear personal ownership;
  • a specific technical or product action;
  • a verified result or defensible qualitative outcome;
  • decisions and trade-offs the user can explain in an interview.

For each project, write:

## <Project name>

<one-line scope and context>

- <action + scope + verified result>
- <decision or technical depth + trade-off + outcome>
- <ownership or collaboration + impact>

**Tech:** <only technologies evidenced by the project>

Prefer two or three strong bullets over exhaustive task lists. Preserve units and measurement context. Avoid first-person pronouns, vague adjectives, keyword stuffing, duplicated achievements, and unsupported leadership verbs. Do not expose private evidence references in the public-facing bullets.

Quality Gate

Before presenting the draft, verify:

  1. Every bullet maps to a reviewed, confirmed source claim.
  2. Personal and team outcomes are not conflated.
  3. Numbers match their source and include meaningful context.
  4. The same accomplishment is not repeated across projects.
  5. Language and tense are internally consistent.
  6. Confidential information is generalized or omitted.
  7. The user could answer “why,” “what,” and “how” for every bullet.

List excluded claims and why they were excluded.

Save

Preview the complete Markdown before writing. Save only after approval to:

<vault>/chronicle/resume/YYYY-MM-DD-<target>.md

Do not overwrite an existing export without explicit confirmation. Report the projects included, claims excluded, output path, and whether any review remains.

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.