Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dcassil/resume-kit --skill learn-terminologygit clone --depth 1 https://github.com/dcassil/resume-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dcassil/resume-kit/learn-terminology)<a href="https://agentmods.dev/skills/dcassil/resume-kit/learn-terminology"><img src="https://agentmods.dev/badge/skills/dcassil/resume-kit/learn-terminology.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00123 | $0.02760 |
| Opus 5 | $0.00062 | $0.01380 |
| Sonnet 5 | $0.00025 | $0.00552 |
| Haiku 4.5 | $0.00012 | $0.00276 |
Grade A, and why
learn-terminology scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Renamed:
learn-terminologywasmanage-synonymsbefore v1.0.0 (see RIT-A-0005).
learn-terminology — propose → truth-gate → confirm → append aliases
Purpose
check-keywords and check-gaps score a
resume against a job deterministically — no LLM at scoring time. Matching
uses a packaged seed lexicon UNIONed with an optional project alias file
(resume-kit/learning/synonyms.json, RIT-T-0068 format). When a scoring run
marks a job keyword as "missing" but the resume already demonstrates that exact
skill under a different name, the deterministic engine simply doesn't know the
two terms are the same thing yet.
This skill is the agent-side growth loop that teaches it: the agent PROPOSES a synonym, the user CONFIRMS it, and the agent APPENDS a justified alias to the project file. From then on the deterministic run matches it — no LLM required at scoring time, ever. The agent only writes data; it never makes scoring smarter at runtime.
Define the workflow ONCE (here) so the three scoring skills link to it rather than copy-pasting divergent copies.
Automatic accepted-edit growth
The edit-session commit path also self-heals the same project alias file for a
narrow, already-confirmed case: when the user accepts or edits a terminology
proposal that mirrors the employer's wording, commit-session derives the token
swap and appends the project alias automatically with source: "accepted_edit" provenance and the caller-supplied timestamp. Rejected,
skipped, undone, auto-mode, non-terminology, malformed, and empty mappings do
not grow aliases.
That automatic path complements this skill; it does not replace it. Use this manual workflow when a scoring run reports a missing keyword and no accepted terminology edit exists yet. The manual path still requires truth-gating and explicit user confirmation before writing.
Run me in a subagent
This is a self-contained, file-mutating task. The main agent should dispatch it
to a subagent (e.g. the Task tool / a general-purpose agent), consistent with
parse-resume and parse-job. Hand the subagent: the list of candidate
(missing job keyword, resume term it may equal) pairs, the path to
resume-kit/config.json, and this skill. The subagent runs the gate, gets user
confirmation, appends → and returns only what it added (canonical, alias,
why) plus what it rejected/deferred. Do NOT stream the full resume/job text back
into the main context.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 240 lines · 123 tokens per session scan A d15f393b12e9
learn-terminology is a skill published in the GitHub repository dcassil/resume-kit (0 stars, last pushed 27d ago), licensed Apache-2.0. It adds 123 tokens to every session and 2,760 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…