Install
$ agentstack add skill-ledq-resumery-bank-map ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
/bank-map: regenerate the evidence map
bank/evidence_map.md is a derived index of bank/experience_bank.md, read by the draft stage to turn its JD-coverage pass into a lookup instead of a per-run re-derivation. It is never a source of truth: every resume claim traces to the bank, and on any disagreement the map is stale and the bank wins. Regenerate it whole: read the entire bank fresh and rewrite the file; do not patch the old map.
Structure (three sections, in this order)
- Requirement lookup: what JDs ask → strongest bank evidence, grouped under theme
headings (platform/backend, full-stack/frontend, data engineering, cloud/DevOps, databases/performance, ML/AI, systems/embedded, collaboration/communication; adjust themes to what the bank actually contains). Each line: the requirement as JDs phrase it → the evidence, tagged with [role_id], plus the headline facts and a production/ deployed marker where true.
- Angle inventory: one entry per bank unit (each contribution and project). Header
carries [role_id], ownership (sole/partial), and status (production, POC, shipped, competition). Body lists the distinct honest facings the unit supports (e.g. a config platform may face schema design, API design, distributed systems, and IaC), each angle with the exact facts (numbers, tools, tradeoffs, outcomes) behind it.
- Absences and standing adjacency candidates: bank-wide absence facts (languages,
clouds, platforms, role types the bank does NOT evidence), verified by scanning the whole bank, so the drafter can settle gap verdicts without a full re-scan; then the nearest-honest-evidence candidates for requirements that recur in postings, marked explicitly as per-JD decisions.
Rules
- Facts, never prose. Telegraphic fragments only; no sentence that could be lifted
onto a resume. If an entry reads like a finished bullet, break it back into facts.
- Numbers verbatim from the bank. Metrics, costs, scale, dates: copy exactly; never
round further or extrapolate.
- Every entry keyed.
[role_id]on everything, so the drafter maps evidence to
resume structure without re-reading headers.
- Angles must be honest facings, not aspirations. An angle exists only if the bank's
facts under it would survive the evaluator's grounding check on their own.
- Absence claims are claims. State an absence only after checking the entire bank,
including the projects and skills sections.
- Never launder placeholders. Bracketed TODOs or unfilled fields in the bank are not
facts; where a unit has them, note the boundary ("do not claim beyond the above").
- Stamp it. Open the file with the generation date, the regeneration command, and
the derived-not-source contract.
When done, confirm the map's unit count matches the bank's (every contribution and project has exactly one angle-inventory entry) and stop.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ledq
- Source: ledq/resumery
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.