review-dictionary-requests
Skill3.6k starsChanged yesterdayMITView on GitHub
Review Freehire dictionary requests from /dictionary, classify duplicates and ambiguous terms, implement useful vocabulary additions, and reconcile request statuses when authorized.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Who's talking about strelov1/freehire
- speedyapply/JobSpy“Feature Request: add freehire.me as a source (public API, no proxy needed, aggregates 227 boards)”GitHub · Aug 16, 2026 · 5 reactions
- alex-denisov/openqareer“feat(sources): полный текст вакансий VK (B641)”GitHub · Nov 10, 2026
- alex-denisov/openqareer“feat(sources): доски iCIMS, Jobvite и Oracle из freehire (B641)”GitHub · Nov 10, 2026
- strelov1/freehire-mcp“Connect Freehire plugin to OAuth account tools”GitHub · Nov 4, 2026
- factwright/factwright“Filling applications on SmartRecruiters' newer form, SAP SuccessFactors, iCIMS and Oracle Taleo”GitHub · Oct 24, 2026
The biggest 5 of 35 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 35
Talked about on GitHub and Bluesky (35 times).
On GitHub · 34
- Aug 16, 2026Feature Request: add freehire.me as a source (public API, no proxy needed, aggregates 227 boards) — speedyapply/JobSpy5 reactions · 1 comment
- Nov 10, 2026feat(sources): полный текст вакансий VK (B641) — alex-denisov/openqareer0 reactions
- Nov 10, 2026feat(sources): доски iCIMS, Jobvite и Oracle из freehire (B641) — alex-denisov/openqareer0 reactions
- Nov 4, 2026Connect Freehire plugin to OAuth account tools — strelov1/freehire-mcp0 reactions · 1 comment
- Oct 24, 2026Filling applications on SmartRecruiters' newer form, SAP SuccessFactors, iCIMS and Oracle Taleo — factwright/factwright0 reactions
29 more on GitHub
- Oct 21, 2026FMHY suggestions 2026-10-21 — sudosilo/free-as-in-links0 reactions
- Sep 15, 2026fix: update minio images as the original repo is no longer available — overhangio/tutor-minio0 reactions · 2 comments
- Aug 17, 2026refactor(google): extract job records from AF_initDataCallback payload — amikai/openings-mcp0 reactions
- Aug 16, 2026Add freehire.me as a job source — full JD text in the search response — he-yufeng/FindJobs-Agent0 reactions · 2 comments
- Aug 16, 2026Add freehire.me as a source — a wider pool for the agents to reject from — VonTerraProject501c3/slushpile0 reactions · 1 comment
- Aug 16, 2026Add freehire.me as an aggregator source — aggregated, but still the employer's own links — vesaias/JobNavigator0 reactions · 2 comments
- Aug 16, 2026Add freehire.me as a listing source — pre-tagged fields to score against — Keljian/JSE0 reactions · 1 comment
- Aug 16, 2026Add freehire.me as a discovery source — a stable front end for the pipeline — leopu00/job-hunter-team0 reactions
- Aug 16, 2026Add freehire.me as a source — normalized results, no scraping layer — BjornMelin/ai-job-scraper0 reactions
- Aug 16, 2026Add freehire.me as a source — an HTTP call instead of a scrape — saeedkolivand/ai-job-hunter-app0 reactions · 1 comment
- Aug 16, 2026Add freehire.me as a job source — no extra account, real ATS links — suxrobGM/jobpilot0 reactions · 3 comments
- Aug 16, 2026Add freehire.me as a source — key-free, read-only, nothing to store — cboyd0319/JobSentinel0 reactions
- Aug 16, 2026Add freehire.me as a provider — one call covering 227 aggregated sources — ever-jobs/ever-jobs0 reactions · 1 comment
- Aug 16, 2026Add freehire.me as a source — 227 boards behind one key-free API — amikai/openings-mcp0 reactions · 1 comment
- Aug 16, 2026Add freehire.me as a source — sponsorship is a server-side filter, so the pre-screen gets cheaper — abhishektuteja01/ApplYourself0 reactions · 1 comment
- Aug 16, 2026Add freehire.me as a fetch source — public ATS data, already aggregated and tagged — perryvegehan/PWP_jobhunt0 reactions
- Aug 16, 2026Add freehire.me as a discovery source — ATS boards already aggregated, no tokens — aravindpranav/job-agent0 reactions
- Aug 16, 2026Add freehire.me as a discovery provider — no API key needed for self-hosted runs — girshovich/job-hunter0 reactions
- Aug 16, 2026Add freehire.me as a source — 294K company career pages behind one key-free API — replyre/job-hunter0 reactions
- Aug 16, 2026Support for freehire.me — key-free API source that aggregates 227 boards — DaKheera47/job-ops0 reactions
- Aug 16, 2026提议:新增职位搜索渠道(freehire.me,零配置免登录)/ Proposal: a zero-config jobs channel — Panniantong/Agent-Reach0 reactions
- Jul 23, 2026chore(freehire-search): migrate freehire.dev → freehire.me — ai-job-search-dev/ai-job-search0 reactions
- Jul 21, 2026Add freehire — awesome-selfhosted/awesome-selfhosted-data0 reactions
- Jul 9, 2026Add freehire-search: country-agnostic freehire.dev aggregator skill — ai-job-search-dev/ai-job-search0 reactions · 2 comments
- Jul 8, 2026Add a freehire-search skill — one aggregator skill covering many boards & countries — ai-job-search-dev/ai-job-search0 reactions · 4 comments
- Jun 17, 2026Add freehire (open-source IT job aggregator) — idimetrix/awesome-job-boards0 reactions
- Jun 17, 2026Add freehire (open-source IT job aggregator) — trinhminhtriet/awesome-job-boards0 reactions
- Jun 17, 2026Add freehire (open-source IT job aggregator) — tramcar/awesome-job-boards0 reactions
- Jun 17, 2026Add freehire (open-source IT job aggregator) — emredurukn/awesome-job-boards0 reactions · 1 comment
On Bluesky · 1
- Oct 21, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 strelov1 / freehire ⭐ 2,017 (+405) 🗒 Go freehire — the open-source search engine for job seekers — @github-trending.bsky.social0 likes and reposts · 1 reply
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- design-system/AGENTS.mdAGENTS.md
- extension/AGENTS.mdAGENTS.md
- web/AGENTS.mdAGENTS.md
- .cursor/rules/commit-checks.mdcCursor rule
- code-reviewSkill
- verify-freehireSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Read root AGENTS.md for current production access, .out-of-scope/README.md, and the AGENTS.md of the requested dictionary.
- Distinctive: line 17
Use the established SSH/Postgres access.
- Distinctive: line 27
Add alias: existing concept, new spelling.
- Distinctive: line 28
Add concept: a distinct, useful skill, specialization or company industry.
- Distinctive: line 32
Search dictionary mappings, descriptions, ambiguity gates, tests and exclusion comments.
- Very specific: line 46
Use the existing thematic dictionary tables.
- Distinctive: line 59
Test canonicalization and realistic prose for the accepted spellings.
- Distinctive: line 72
When queue updates are authorized, close existing supported terms as accepted, and clear confirmed test noise or unsupported requests as …
- Very specific: line 75
Use a transaction and explicit reviewed ids with WHERE status = 'pending' and RETURNING.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review dictionary requests
Work from the repository root. The public /dictionary page describes the vocabulary;
submitted requests live in production dictionary_gaps, not on that page.
Inspect the queue
Read root AGENTS.md for current production access, .out-of-scope/README.md, and the
AGENTS.md of the requested dictionary. Inspect the schema in
migrations/0188_dictionary_gaps.sql, later migrations affecting it, and
internal/platform/db/queries/dictionary_gaps.sql before querying.
Use the established SSH/Postgres access; keep credentials out of output.
Fetch every pending row, including id, kind, raw_term, normalized_term, request_count, first_requested_at, last_requested_at and resolution_note. Fetch status totals separately. Dates are request dates, not proof of when a human last reviewed the queue. Avoid exposing submitter identities.
Complete the inspection with one disposition for every pending row:
- Already supported: identify the canonical and verify actual canonicalization.
- Add alias: existing concept, new spelling; preserve the canonical slug.
- Add concept: a distinct, useful skill, specialization or company industry.
- Needs clarification: multiple meanings, combined concepts, or insufficient evidence.
- Reject: test noise, wrong vocabulary kind, or a documented exclusion that still applies.
Search dictionary mappings, descriptions, ambiguity gates, tests and exclusion comments. A string match alone does not prove a term resolves. Preserve the separation between skill, role, seniority and company industry. Broad occupational skills can be valid; being nontechnical alone is not grounds for rejection. Consult primary product documentation when a product's identity or scope is uncertain.
Implement authorized additions
A request to inspect or discuss produces a proposed disposition. A request to add useful terms authorizes the corresponding repository edits. Keep uncertain items pending and explain the specific ambiguity rather than inventing aliases.
For skills, follow internal/dict/skilltag/AGENTS.md: alias mappings, display labels
where mechanical title casing is insufficient, and descriptions belong together.
Use the existing thematic dictionary tables. After adding canonical skills, read
internal/dict/skillvec/AGENTS.md and run go generate ./internal/dict/skillvec/
to append their permanent vector positions; preserve existing indices. Run
make gen-contracts and commit the generated web vocabulary and descriptions too. Read the corresponding owners for
specializations and industries instead of treating them as skills.
Choose canonical spellings deliberately. Correct a submitted typo into its actual
concept; a one-off typo need not become a permanent prose alias. Check whether an
alias is a common verb or ordinary phrase: design systems also occurs in
"design systems that scale". Respect intentional exclusions and the distinction
between structured-list canonicalization and prose parsing. New strong phrase
matches can also corroborate nearby ambiguous skills; inspect that effect.
Test canonicalization and realistic prose for the accepted spellings. Add negative examples when ambiguity warrants them. Run the affected dictionary tests and the repository's applicable checks, including Go vet and integration-tag compilation. Review only this task's diff; preserve unrelated work.
Reconcile only what is live
Code prepared locally is not a deployed dictionary. Keep new requests pending until production resolves them. Deployment and catalogue backfill are separate actions: follow the user's authorized scope and the worker/deployment instructions before running either. Existing job facets need backfill and search refresh as documented by the dictionary owner.
When queue updates are authorized, close existing supported terms as accepted,
and clear confirmed test noise or unsupported requests as rejected with an English
resolution_note. For new additions, verify live resolution before acceptance.
Use a transaction and explicit reviewed ids with WHERE status = 'pending' and
RETURNING; compare changed rows with the intended set before committing. Preserve
request counts and timestamps. Re-read the affected rows after committing.
Accepted rows remain live under a partial unique index; rejected terms may be
submitted again. Do not delete request history or bulk-close the pending queue.
Report added concepts and aliases separately, closed requests, items still pending, checks actually completed, and whether the result is local or deployed. Link the changed artifacts. Do not claim acceptance, deployment or backfill from local tests.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

