telemetry
claudePlugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
Choose a professional certification specification-first rather than market-first. create-workspace stands the search up as a private GitHub repo instantiated from the Spec-Led-Certification template, so it survives the machine and its history shows when the scorecard was frozen. Three entry points for the three situations: start-search onboards and runs the full intake, rerun-search archives the previous run and reports what moved in the market, update-profile changes what is stored about you and marks the scorecard stale. Intake writes five dated profile files — subject, current position read from evidence, learning preferences, objectives and standing positions, money and time — a weighted scorecard is derived from those alone and frozen before any credential is looked up, then candidates are scored against it with a source tier and confidence tag on every number. Hard requirements exclude rather than score down. Emits a ranked comparison and a Typst PDF whose figures are computed from the CSVs at compile time. All state lives in the working directory, never in an agent memory store.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin spec-led-certification in danielrosehill/spec-led-certification-plugin. Commands read from the repo's manifest — 1 month ago.
benchmark-meEstablish where the user actually stands today against the capability areas in the spec, from evidence they point at — repos, site, CV, published work — rather than self-report alone. Writes profile/benchmark.md. Second stage of the spec-led certification workflow.
build-scorecardDerive weighted, anchored scoring criteria and hard filters from the completed profile, then freeze them before any credential is researched. Writes scorecard/criteria.csv, scorecard/filters.csv and scorecard/methodology.md. The pivot of the spec-led certification workflow — run after intake, before
create-workspaceCreate a private GitHub repository from the Spec-Led-Certification template and clone it, as the durable home for one certification search. Use when the user wants the search backed by a repo rather than a local folder — "make a repo for this", "set up a workspace for finding a certification". For a
define-budgetCapture the two budgets — money (ceiling, comfortable figure, retakes, who pays, renewals) and time (hours per week, weeks available, whether the time is protected). Writes profile/budget.md. Fifth and final intake stage of the spec-led certification workflow.
define-objectivesEstablish what the credential is actually for — its purpose, its audience, the user's standing positions such as vendor neutrality, the calendar window, and the condition under which sitting nothing is the right answer. Writes profile/objectives.md. Fourth stage of the spec-led certification workflo
define-specCapture the headline ask — what field the user wants certified in, which capability areas the credential must cover, and what is out of scope. Writes profile/spec.md. First stage of the spec-led certification workflow; run it before any research.
learning-preferencesCapture how the user learns — modality, devices, session shape, assessment formats they do well and badly in, and what has failed before. Writes profile/learning-preferences.md. Third stage of the spec-led certification workflow; the most durable file in the profile.
recommendTurn the scored research into a recommendation and a typeset PDF — the answer up front, why the runner-up lost, where to invest study effort, and what would change the conclusion. Writes report/meta.yaml and report/narrative.yaml, then builds pdf/certification-report.pdf. Final stage of the spec-led
rerun-searchSecond and later runs — archive the previous run, confirm the profile is still current, re-survey the market and report what changed since last time. Use when the intake is already on file and the user wants to know whether the market has moved, or whether an earlier recommendation still holds. For
research-marketSurvey the certification market against the frozen scorecard — find every plausible credential, apply the hard filters, price the whole route, and score the survivors with a confidence tag and a source for every number. Writes research/candidates.csv, research/scores.csv, research/candidates/*.md an
scaffold-workspaceCreate the directory structure a spec-led certification search writes into — profile/, scorecard/, research/, report/ — by copying the plugin's bundled template into the working directory. Idempotent and non-destructive: it never overwrites a file that already has content. Run this first when starti
spec-led-certificationEntry point for the whole workflow — reads the state on disk and routes to start-search, rerun-search or update-profile. Use when the user wants a certification decision and it is not obvious which of the three they need, or when they do not know what state an existing workspace is in.
start-searchFirst run — onboard someone who has never done this, take them through all five intake interviews, freeze the scorecard, survey the market and produce the recommendation. Use when profile/ is unfilled, when the user is starting a search for a new subject, or when they ask how this works. For a secon
update-profileChange what is stored about the user — their position, learning preferences, objectives, budget or subject — without running a search. Re-interviews only the files that changed, re-dates them, and marks the scorecard stale so the next run rebuilds it. Use when circumstances change, when a review dat
/spec-led-certification:cert-searchFind a certification worth taking, specification-first — routes to a first run, a re-run against a moved market, or a profile update
intakeInterviews the user and writes the five profile files. Knows nothing about the certification market and must not go looking. Use for the first five stages of the spec-led certification workflow.
recommendationTurns the scored research into a recommendation and a typeset PDF — the answer up front, why the runner-up lost, where to invest effort, and what would change the conclusion. Writes prose only; all figures are computed by the Typst template from the CSVs. Use for the final stage of the spec-led cert
researchSurveys the certification market against a frozen scorecard, applies the hard filters, prices the whole route, and scores survivors with a source and confidence tag for every number. Receives the scorecard and never sees the intake conversation. Use for the research stage of the spec-led certificati
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Governed catalog discovery for Informatica Intelligent Data Management Cloud (CDGC): find tables, columns, files, glossary terms and policies across the enterprise catalog, check ownership, certification, sensitivity and applicable policy, and get safe-usage guidance grounded in catalog metadata before querying any data. Requires an Informatica IDMC tenant and the Informatica Catalog Discovery connector.
1 skill · 2 MCP servers
Governed catalog discovery for Informatica Intelligent Data Management Cloud (CDGC): find tables, columns, files, glossary terms and policies across the enterprise catalog, check ownership, certification, sensitivity and applicable policy, and get safe-usage guidance grounded in catalog metadata before querying any data. Requires an Informatica IDMC tenant and the Informatica Catalog Discovery connector.
1 skill · 2 MCP servers
Organic LinkedIn presence, end to end, with LinkedIn's own rules enforced in code. Orchestrator (context: fork) gates every request against User Agreement §8.2 — refusing automation, scraping, engagement pods, bulk DMs, fake identity and fabricated proof, each with a compliant substitute — then routes to profile / strategy / content / engagement / analytics. Headline and whole-profile scoring with fixes ranked by points per hour; positioning brief with a mandatory exclusion list; cadence priced against real hours with a 90-minute floor; newsletter eligibility + six-month sustainability gate; post linter blocking on engagement bait and screen-reader-hostile Unicode pseudo-bold; repurposing with a reuse ledger; capped commenting roster and template-refusing outreach; analytics that test patterns against a seeded permutation null and refuse to conclude below 10 posts. 17 stdlib tools, 15 references with per-claim confidence levels. No credentials, no API calls, nothing auto-sent. Answers discussion #934.
6 skills · 8 commands · 2 agents
Remove multi-vendor AI provenance marks from text, images, documents, and media. Bundles the remove-ai-marks and clean-user-facing-text skills.
2 skills · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.