Rank truthful improvement candidates for a pending change with the deterministic rank-edit-candidates surface. The skill passes candidates, FeatureContext, optional preferences, and aliasfile to the CLI/MCP/facade surface, then presents the ranked candidates and reasons. It never edits the resume; chosen candidates…
Compatibility entry-point guide for the resume-intelligence end-to-end workflow. Use when a user asks for the older resume-workflow guide; it points to complete-resume-flow and the four composable flow skills rather than duplicating their stage gates.
Dispatch a subagent to review a resume against the original resume and the target job, then write STRUCTURED, parseable findings to resume-kit/review/ .md. The reviewer checks truthfulness (claims not supported by the original), missed JD requirements, over/under-claims, terminology-mirroring opportunities, and…
Seed and grow the project synonym index (aliasfile) automatically during the normal tailoring flow, so match / check-keywords / check-gaps / suggest-terminology are alias-aware from the very FIRST score instead of aliasfile being None on a fresh project. Runs after a resume + job are both active: proposes TRUTHFUL…
Job-specific tailoring over a prepared resume, active job, and durable learning/evidence. Runs the truth-gated scoring, improvement, validation, and re-scoring loop after Flow 1 and Flow 2, then stops before perfect/export. Best run in a subagent.
DEPRECATED one-release alias for update-refine. The job-independent wording pass was renamed from standard to refine in RIT-I-0020; use update-refine to write -refine.json through the build-refine capability.
Update MISSING-BUT-TRUE keywords into the resume, truth-gated, no LLM. When a deterministic gap run (check-gaps) reports a JD keyword as missing from THIS resume but the candidate's MASTER resume proves they genuinely have it, this workflow creates targeted ChangeProposal records and drives the code-owned edit-session…
Produce the resume's refine version from structure/base: run the best-practices score, auto-apply the truthful autosuggestible rewrites, elicit the user's real facts for needsuserinput items, and write -refine.json behind the claim-preservation gate — then point config's refine at it. Truth-gated, no fabrication. Best…
Produce the resume's structure version from base: run deterministic shape analysis, apply auto-safe canonical section shaping behind the content-ledger and cross-section claim gates, surface ambiguous section mappings for the user's decision, and write -structure.json only when the gates pass. Deterministic…
Produce the resume's base version: run the deterministic ATS structural check, then apply auto-safe structural fixes (strip PII/placeholders, normalize dates and formatting) behind the claim-preservation gate, writing -base.json and pointing config's base at it. Deterministic, no LLM. Judgment/needs-input items are…
Section-by-section terminology update through the code-owned edit-session orchestrator. When deterministic scoring finds a JD keyword the resume already satisfies under a different surface form, this skill uses suggest-terminology to enumerate truthful wording swaps, converts accepted candidates into ChangeProposal…
Deterministically validate resume facts against candidate evidence records. Returns a TruthReport flagging unsupported or contradicted claims. No LLM required.