agentleFS
thituongh699-hashthituongh699-hash/oriward/.agents/skills/job-analysis/SKILL.md

job-analysis

Skill2 starsChanged 7 days agoMITView on GitHub

Understand a saved role's mission and core deliverables, map current evidence and run a simulated hiring review. Use for specific JD fit and resume assessment, not vacancy discovery.

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. rishb0/resume-harness★ 0same 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.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When analysis is requested, explain the role's purpose and 2–4 deliverables before rating.

    line 8
  2. Distinctive:

    When needed, research public company sources.

    line 12
  3. Very specific:

    If review is requested after drafting, use review packet --resume-id <id> --compact on the exact version.

    line 14
  4. Very specific:

    Use deterministic commands for validation, grading and versions.

    line 16
  5. Distinctive:

    Keep confirmed/document-verified evidence separate from inference.

    line 20
  6. Very specific:

    Update pipeline to evaluating|shortlisted|parked|discarded with the reason.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Job analysis and hiring review

When analysis is requested, explain the role's purpose and 2–4 deliverables before rating. Reuse this context downstream; review is optional and never a writing/export prerequisite. Respect deferral without claiming completion.

  1. Obtain analysis packet --job-id <id> --compact. Read the primary JD first; references can enrich interpretation, but its purpose, 2–4 deliverables and gates control this analysis. Then read the full experience index and relevant details in batches. Select evidence semantically, never by similarity/keywords. analysis draft is all-unknown.
  2. Preserve primary-JD quotes. Internally map requirements to evidence, factual status and truthful wording; no rigid per-requirement prose. Mark met only with current sourced experience, self-reports/confirmed assertions or document-verified sources. Split compound tasks; missing evidence is not absence.
  3. When needed, research public company sources; retain URL/date and separate fact from inference. Availability must refer to this posting. Refresh closed sources.
  4. Load references/analysis-contract.md to save analysis and conduct red/blue review. Set coverage confirmed only after checking the full JD. Save with python -m oriward analysis save --file <json>, then inspect a fresh packet.
  5. If review is requested after drafting, use review packet --resume-id <id> --compact on the exact version; explain fit, strengths, gates, questions and interview themes. Continue with interview-coach using the same IDs. A–D is supplementary; do not inflate met. Re-review revisions; stop after two rounds without new evidence.

Use deterministic commands for validation, grading and versions. Keep bulk output on disk via global --output <path> before the domain. Grades simulate recruiting risk; they never predict or guarantee offers.

Career Twin Core contract

  • Keep confirmed/document-verified evidence separate from inference. Hiring motives from public business context remain hypotheses unless directly sourced. Reuse role_focus deliverables, resume themes and interview themes downstream instead of repeating the whole experience interview.
  • Update pipeline to evaluating|shortlisted|parked|discarded with the reason. Propose only useful targeted follow-ups with action propose (source_type:job) and suggestion_reason; do not create a whole-library evidence/approval queue.
  • Cite confirmed hard-constraint assertion IDs and park/discard a conflicting job. Record recommendations and changed-evidence reassessment through the decision contract; shared rules are in AGENTS.md.

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.