resume-writer — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited resume-writer (Agent Skill) and scored it 75/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 6 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 6 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Rewrite, audit, score, and target resumes with measurable impact, recruiter skim value, and role-specific positioning.
resume-writer.Rewrites resumes using a persistent, user-curated library of principles harvested from recruiters, hiring managers, and HR professionals. Every change made is traceable back to a specific principle in insights/principles.md or a pattern in references/common-patterns.md.
tips/ is the staging area for newly collected posts, weekly review packets, and candidate advice that has not yet been promoted into the authoritative library. Use it to keep the skill current without treating every fresh post as permanent truth.
This skill operates in one of three modes. Detect which one before proceeding.
Triggered when the user provides a resume (pasted, .docx, .pdf, or screenshot) and asks for a rewrite, review, audit, or critique.
Go to the Enhance Workflow section.
Triggered when the user pastes or uploads a recruiter/HR post and says something like "rw add", "add to library", "add this insight", or pastes a post without a resume present.
Go to the Add Insight Workflow section.
Triggered when the user asks to refresh, review, triage, summarize, or organize recruiter/HR posts for future resume guidance, or refers to the weekly tips/ update.
Go to the Refresh Tips Workflow section.
tips/ contents, use Refresh Tips mode.Default output mode is human.
json-output-spec.md is the authoritative contract for machine-readable output.
Switch output mode when user intent indicates automation needs:
json or both.Mode behavior:
human: return the standard readable audit output.json: return valid JSON only, matching json-output-spec.md.both: return standard readable audit first, followed by a JSON block that matches json-output-spec.md.Hard enforcement rules:
json mode, return valid JSON only.json mode, do not use markdown fences.json mode, do not include prose outside the JSON object.both mode, the JSON block must still fully conform to the schema.json-output-spec.md.null or an empty array instead of guessing.Read before enhancing or auditing a resume; also read the scoring reference for score outputs. Full workflow. Paths mentioned in that reference are relative to this skill directory. Its rules are required for the selected mode.
Read whenever scoring a resume or producing machine-readable scores. Full workflow. Paths mentioned in that reference are relative to this skill directory. Its rules are required for the selected mode.
Read only for Add Insight mode. Full workflow. Paths mentioned in that reference are relative to this skill directory. Its rules are required for the selected mode.
Read only for Refresh Tips mode. Full workflow. Paths mentioned in that reference are relative to this skill directory. Its rules are required for the selected mode.
insights/principles.md and references/common-patterns.md are authoritative for normal audits.insights/principles.md or references/common-patterns.md cannot be read, continue in degraded mode and clearly state that the audit is limited.insights/principles.md, return exact append ready principle text and state that manual update is required.tips/ files cannot be read, continue without them. Do not pretend fresh-source review was performed when the staging files were unavailable.If the user is not sure how to use this skill, asks what it needs, or asks for examples:
Minimum useful input:
Example prompts:
Use resume-writer to rewrite my resume for a PowerShell automation engineer role.Score this resume against the job posting and tell me what needs to change first.Show me an example prompt for using this skill with a resume and target job description.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.