agentleFS
ErayAcikgzErayAcikgz/larping-skill/SKILL.md

larp

Skill2 starsChanged 34 days agoMITView on GitHub

Strengthen real CV, portfolio, cover-letter, and professional-profile material without exaggeration. Use when the user asks to larp, sharpen, position, or make genuine experience sound more technically compelling.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. Jakeschincariol/claude-illegal-codes★ 11same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    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:

    Keep uncertainties visible.

    line 72
  2. Distinctive:

    Use the Artifact Router. Match the requested language, grammatical person, level of formality, and length.

    line 91
  3. Distinctive:

    Prefer precise verbs that fit the evidence, such as contributed, designed, integrated, implemented, verified, analyzed, or supported.

    line 94
  4. Distinctive:

    Do not add a result merely because a strong bullet appears to need one.

    line 96
  5. Distinctive:

    Before delivery, run four checks:

    line 100
  6. Distinctive:

    If the evidence is clear, provide the rewritten copy first.

    line 111
  7. Distinctive:

    If evidence is thin, provide a cautious draft and one or two questions that could unlock stronger wording.

    line 113
  8. Distinctive:

    Never invent experience, ownership, results, credentials, seniority, or metrics.

    line 138
  9. Distinctive:

    Ask only questions whose answers would materially improve accuracy or positioning.

    line 141

≈ “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

Larp

Turn genuine experience into clear, technical, and consequential professional writing. Preserve the truth. Strengthen the framing. Never invent the work.

When to Use

User asks to strengthen professional material
  ├─ Evidence is specific enough → Rewrite with a claim check when needed
  └─ Evidence is too thin → Draft cautiously and ask focused questions
  • User asks to larp, sharpen, position, or strengthen professional material.
  • A CV bullet, portfolio page, cover letter, LinkedIn profile, or project summary is accurate but undersells technical work.
  • A user wants help expressing a real contribution without crossing into exaggeration.

When NOT to Use

  • The user asks to invent experience, results, credentials, seniority, or ownership.
  • The requested text is unrelated to professional positioning.
  • The user wants a verbatim transcription or explicitly does not want wording changed.
  • The user needs factual research, reference checking, or a recommendation rather than a rewrite.

Quick Reference

Evidence-to-Claim Map

Evidence availableStrongest defensible framingDo not imply
A completed technical taskDesigned, implemented, integrated, or verified the stated taskScope beyond the described work
Collaborative contributionContributed to, supported, or worked within a team on the stated areaSole ownership or leadership
Bench or simulation testingValidated, tested, analyzed, or investigated the stated behaviorProduction qualification or final performance
A tool or technology usedApplied, used, or worked with it in the stated contextDeep expertise, certification, or ownership
A stated resultReport the result with its condition or contextGeneralized business impact or unverified metrics

Artifact Router

ArtifactPrioritizeFormat
CVContribution, technical context, supported purpose or resultConcise bullet
PortfolioProblem, scope, decisions, contribution, validation, statusStructured narrative
Cover letterTransferable capability matched to the roleRole-specific paragraph
Professional profileTechnical identity and evidence-backed focus areasShort summary

Claim-Risk Check

SignalAction
The wording adds a named role, metric, or outcomeRemove it unless the user provided it
The wording turns team work into "led" or "owned"Use a contribution verb or ask for confirmation
The input says "tested"State what was tested and avoid implying certification
The source is vagueUse narrow wording and ask one focused question

Implementation

Step 0: Extract Evidence

Separate what is known from what is only plausible.

  1. Identify the system, domain, and technical context.
  2. Identify the user's actual actions, decisions, tools, and validation work.
  3. Mark ownership, collaboration, outcomes, and metrics only when directly supported.
  4. Keep uncertainties visible. Do not convert an inference into a claim.

Step 1: Select the Strongest Truthful Angle

Favor details that show engineering judgment:

  • Design choices and constraints
  • Integration between components or disciplines
  • Debugging, testing, analysis, and verification
  • Tradeoffs, interfaces, and technical scope

Turn a task list into a contribution statement where the evidence allows it:

contribution → technical context → method or decision → supported purpose or result

Step 2: Route and Rewrite

Use the Artifact Router. Match the requested language, grammatical person, level of formality, and length.

  • Preserve collaboration accurately.
  • Prefer precise verbs that fit the evidence, such as contributed, designed, integrated, implemented, verified, analyzed, or supported.
  • Replace generic verbs only when the source identifies a more specific action.
  • Do not add a result merely because a strong bullet appears to need one.

Step 3: Verify

Before delivery, run four checks:

TestPass criterionFail action
Evidence fidelityEvery substantive claim appears in the supplied evidenceRemove or narrow the claim
Scope accuracyOwnership and collaboration match the sourceUse a weaker role verb or ask
Technical clarityThe wording makes the relevant technical context visibleAdd supported context
Professional usefulnessThe result fits the requested artifact and lengthReformat or tighten

Step 4: Deliver

If the evidence is clear, provide the rewritten copy first. Add a short explanation only if the user asks for one.

If evidence is thin, provide a cautious draft and one or two questions that could unlock stronger wording.

For high-stakes or ambiguous material, append:

Supported claims: [claims grounded in the source]
Questions to unlock stronger wording: [only essential questions]
Claims to avoid: [wording that would overstate the evidence]

See examples.md for complete transformations and test-results.md for evaluated guardrail cases.

Common Mistakes

MistakeFix
Replacing a weak verb with a stronger but unsupported oneRecover the specific action from the evidence first
Treating tool exposure as expertiseState the tool and context, not an unsupported proficiency level
Making collaboration invisibleName the contribution without claiming team-level ownership
Hiding uncertainty with polished languageKeep conditions, scope, and status explicit
Adding metrics for impactAsk for a metric or state the supported qualitative outcome

Constraints

  • Preserve facts, scope, and uncertainty.
  • Never invent experience, ownership, results, credentials, seniority, or metrics.
  • Match the input language unless the user requests another language.
  • Match complexity to the artifact. A CV bullet should not become a portfolio paragraph.
  • Ask only questions whose answers would materially improve accuracy or positioning.

Output

Clear evidence:

Rewritten copy: [final text]

Thin or ambiguous evidence:

Cautious draft: [final text]

Question: [one focused fact needed for a stronger version]

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.