developer-search
/developer-search
Use when mapping technical search opportunities by exact query, intent, and source evidence. Not for inventing search volume, rankings, or time-to-result promises.
- Author
- gosuda ↗
- Repository
- dalcom-skills ↗
- Licence
- Apache-2.0
- Last repository change
- 10.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Use when mapping technical search opportunities by exact query, intent, and source evidence. Not for inventing search volume, rankings, or time-to-result promises.
Original author description
Use when mapping technical search opportunities by exact query, intent, and source evidence. Not for inventing search volume, rankings, or time-to-result promises.
How it works
- What you need before you start
- Reading each query
- Freshness and success signals
- Numbers you may not invent
- What you hand over
SKILL.md preview
--- name: developer-search description: 'Use when mapping technical search opportunities by exact query, intent, and source evidence. Not for inventing search volume, rankings, or time-to-result promises.' --- # Developer search Map which technical queries are worth targeting and what page each one needs. This is read only. Work from public search evidence and any console or rank data the user supplies, which stays optional throughout. Rank trackers and consoles are evidence sources only, never the work itself. This skill does not deploy SEO, build pages, run vendor-automated campaigns, or promise ranks. ## What you need before you start - `queries` (required): candidate exact queries, or a topic the user authorizes for query discovery from public sources. - `evidence` (optional): Search Console exports, rank-tracker data, or docs analytics the user supplies. When absent, proceed on public evidence and mark rows accordingly. ## Reading each query 1. Record each exact query verbatim and give it one intent class: error-message, how-to, implementation, comparison, or reference. Intents stay distinct because each needs a different page type. 2. Attach source evidence to each query: observed discussions, docs gaps, competing answers, or supplied console data with dates. A query with no evidence stays on the map as a candidate with its gap named, or is dropped at the user's choice. 3. Recommend one page type per query (error reference, tutorial, comparison brief, API reference section) and name the competing answer it must beat fairly. ## Freshness and success signals Give every row a freshness trigger (release cadence, API change, new error text) and a measurable success signal (indexed page, docs click-through on a real path, resolved-question rate). A row without both is unfinished. ## Numbers you may not invent Volumes, rankings, traffic forecasts, and timelines appear only with an authoritative source and date. Anything else is marked `UNVERIFIED` or left out. Read the finished map once for unsourced numbers before handing it over. ## What you hand over A search opportunity map in chat: exact queries, intent classes, evidence, page types, named competing answers, freshness triggers, success signals, and a verification note covering every number. Nothing else changes.
Files in this package (2)
- SKILL.md 2 KB
- agents/openai.yaml 1 KB
Versions
The database has no other skills named developer-search.
Database snapshot: 13.11.2026 · package version 016aaffa6c65 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100keyword-research
Use when the user wants keyword research, search intent mapping, keyword clustering or keyword-to-page mapping, or asks what people search for, which keywords to target, which page should rank for a keyword, or how to find local keywords (service + city, "near me",… - 90paid-media-search-query-analyst
Use when Codex should act as the Search Query Analyst specialist from Agency Agents. Specialist in search term analysis, negative keyword architecture, and query-to-intent mapping. Turns raw search query data into actionable optimizations that eliminate waste and amplify… - 85developer-listening
Use when collecting dated per-conversation evidence from public developer discussions to triage opportunities. Not for continuous monitoring, replies, or unsolicited engagement. - 90optimize-search
Improve technical SEO, organic search performance, and answer-engine visibility. Use for SEO audits, keyword or query intent, page optimization, crawlability, indexing, canonicalization, schema, internal linking, content decay, AI answer citations, retrieval, entity clarity, or… - 100serp-analysis
Use when the user asks to "analyze the SERP" or "SERP分析"; maps SERP features, layout, ranking factors, search intent, AI Overviews, and snippet opportunities for a query. Not for keyword demand discovery — use keyword-research. SERP分析/搜索结果 - 100developer-keyword-research
Builds a prioritized keyword list for technical search queries (error strings, "how to X in Y" tasks, integration intents, comparisons, migrations) mined from docs search logs, support tickets, issue trackers and first-party query data rather than keyword-tool volume. Use…