New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

GitHub Lead Qualification

by Ducksss in Ducksss/codex-profiles

A skill your agent uses when qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft.

MITAuto-check passedMarketing & SEO

Install GitHub Lead Qualification

skills CLI
$ npx skills add Ducksss/codex-profiles --skill github-lead-qualification -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Ducksss/codex-profiles github-lead-qualification --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Ducksss/codex-profiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/github-lead-qualification .claude/skills/github-lead-qualification && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
github-lead-qualification
GitHub stars
177
Token cost
~1.2k tokens
SKILL.md length
537 words
Files
3 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft.

  • Works in 8 steps: Select unqualified GitHub targets whose… → Read the target repository, list,… → Check GitHub for existing open PRs and… → …
  • Qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft
  • SKILL.md covers Purpose, Required Context, Boundaries and Accepted Input, plus 3 more sections
  • Calls node

What it does

GitHub Lead Qualification is an agent skill from Ducksss/codex-profiles. Use when qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft. Not for discovery, drafting, outreach, submission, or monitoring.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/icp-rules.md`).

It sits in Marketing & SEO, covering Lead generation. It works with GitHub, OpenAI and Bash. The repository describes itself as: Named CODEXHOME profiles and ChatGPT Desktop windows with separate local state, without copying tokens. The licence is MIT.

When your agent uses it

  • Qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft
  • Tasks that involve Lead generation

Example prompts

  • “/github-lead-qualification”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Select unqualified GitHub targets whose next action is lead qualification.
  2. Read the target repository, list, directory, or guidelines enough to judge
  3. Check GitHub for existing open PRs and issues and the tracker for duplicate
  4. Apply references/icp-rules.md; record evidence links and the truthful-fit
  5. Set Status
  6. Set Priority: P0 for direct Codex, agent, or CLI listing fit; P1 for
  7. Set Next Action = Run closing draft only for ICP: yes targets ready for
  8. Append a Log entry with the decision, reason, evidence URL, and next step.

What it can do on your machine

Read from SKILL.md and the folder at commit dde281b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

GitHub Lead Qualification loads about 1.2k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 537 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Ducksss/codex-profiles at commit dde281b, republished under its MIT licence (© Ducksss). 537 words, ~1,209 tokens.

Download SKILL.mdSave it as .claude/skills/github-lead-qualification/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
github-lead-qualification
description
Use when qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft. Not for discovery, drafting, outreach, submission, or monitoring.

GitHub Lead Qualification

Purpose

Decide whether GitHub lead-gen candidates are real fits for codex-profiles, then update the outreach tracker with evidence and a next phase. This skill consumes tracker targets whose Next Action = Run lead qualification.

Required Context

Read README.md for current product positioning, ops/outreach/launch.md for policy gates, and the selected tracker target for live outreach state. Load references/icp-rules.md before scoring.

Boundaries

  • Update tracker Targets and append Log entries only.
  • Consume tracker targets whose Next Action = Run lead qualification.
  • Use Log.Workflow = lead-qualification for every meaningful decision.
  • Assign exactly one of ICP: yes, ICP: maybe, or ICP: no.
  • Set Priority, Status, Last Checked, Next Action, and evidence.
  • Do not discover new leads.
  • Do not draft PRs, issues, comments, emails, DMs, forum posts, listing submissions, or maintainer replies.
  • Do not contact externally.

Accepted Input

  • Consume only Backlog or Deferred targets whose Next Action = Run lead qualification.
  • Leave ready ICP: yes targets as Backlog with Next Action = Run closing draft; leave all other outcomes with a concrete recheck, blocker, or terminal next action.
  • Issue-first is a valid closing-draft route when the target is a truthful fit, requires an issue before a PR, and has no existing submission.

Tracker Protocol

Create a unique run-<UTC-timestamp>-<random-suffix> <run-id>, list candidate rows, and inspect each selected row before claiming it:

sh
node scripts/outreach-tracker.mjs list --json
node scripts/outreach-tracker.mjs list --status Backlog --json
node scripts/outreach-tracker.mjs list --status Deferred --json
node scripts/outreach-tracker.mjs get <key> --json
node scripts/outreach-tracker.mjs claim <key> --by <run-id>

If claim exits 3, skip the target without writing or contacting externally. After a successful claim, use a shell trap or equivalent finally cleanup to release on every exit path, including partial persistence or logging failure. After qualification, persist the decision and stable phase log:

sh
node scripts/outreach-tracker.mjs upsert <key> --status "<status>" \
  --priority "<P0|P1|P2>" --last-checked <YYYY-MM-DD> \
  --next-action "<next phase, blocker, recheck, or terminal action>" \
  --notes "<ICP decision, rationale, and evidence>"
node scripts/outreach-tracker.mjs log --target <key> \
  --workflow lead-qualification --action Rechecked \
  --result "<ICP decision, reason, and next step>" --link "<evidence-url>"
node scripts/outreach-tracker.mjs release <key> --by <run-id>

Target upserts are idempotent by Key, so retry an upsert after a definite failure. Logs are append-only and each tracker invocation supplies a mutation operation id, so a transport retry cannot append the same event twice.

Show full SKILL.md (244 more words)Show less

Workflow

  1. Select unqualified GitHub targets whose next action is lead qualification.
  2. Read the target repository, list, directory, or guidelines enough to judge fit and contribution route.
  3. Check GitHub for existing open PRs and issues and the tracker for duplicate repository URLs or keys before marking a target drafting-ready.
    • If an existing submission is open, preserve the target and history, set Issue Open or PR Open and route the canonical link to monitoring. Do not create a closing draft.
    • If multiple tracker rows describe the same repository, preserve them, set a concrete dedupe blocker, and route the conflict through Merge Queue.
  4. Apply references/icp-rules.md; record evidence links and the truthful-fit rationale.
  5. Set Status:
    • Backlog only for ICP: yes with a valid PR-first or issue-first route, no duplicate open PR or issue, and a concrete next action.
    • Deferred for ICP: maybe, temporary blockers, gated flows, or unresolved tracker dedupe conflicts.
    • Dead for permanent ICP: no mismatches.
  6. Set Priority: P0 for direct Codex, agent, or CLI listing fit; P1 for likely Codex or CODEX_HOME workflow fit; P2 for broader devtool visibility.
  7. Set Next Action = Run closing draft only for ICP: yes targets ready for drafting. Otherwise set a specific recheck, blocker, or terminal note.
  8. Append a Log entry with the decision, reason, evidence URL, and next step.

Output

Return a concise tracker handoff: targets qualified, ICP counts, blockers, targets ready for closing draft, and any records that need dedupe cleanup.

© Ducksss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/github-lead-qualification of Ducksss/codex-profiles.

  • SKILL.md
  • agents/openai.yaml
  • references/icp-rules.md

Open the folder on GitHubat commit dde281b

Compare with similar skills

GitHub Lead Qualification next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

GitHub Lead Qualification compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
GitHub Lead Qualification this skillDucksss/codex-profiles177—~1.2kAutomated safety check: PassMIT
GitHub Repo Signalsgooseworks-ai/goose-skills1.2k1 repos~2.6kAutomated safety check: NotesMIT
Generative Engine Optimizationkostja94/marketing-skills1k—~2.9kAutomated safety check: PassMIT
GitHub Project Contributor Finder API Skillbrowser-act/skills6.1k1 repos~1.9kAutomated safety check: PassMIT
Geo Fundamentalswasp-lang/wasp19k8 repos~861Automated safety check: PassMIT
SEO GeoReScienceLab/opc-skills1.8k4 repos~2.1kAutomated safety check: PassApache-2.0

Similar skills

  • GitHub Repo Signals

    gooseworks-ai/goose-skills

    Extract and score leads from GitHub repositories by analyzing stars, forks, issues, PRs, comments, and contributions.

    1.2k GitHub starsUsed in 1 repo~2.6k tokens
    Marketing & SEOAuto-check: notes

  • Generative Engine Optimization

    kostja94/marketing-skills

    When the user wants to optimize for AI search visibility (ChatGPT, Claude, Perplexity, AI Overviews).

    1k GitHub stars~2.9k tokensUpdated yesterday
    Marketing & SEOAuto-check passed

  • GitHub Project Contributor Finder API Skill

    browser-act/skills

    This skill helps users extract GitHub repository project details and contributor contact information using keywords, stars, and update dates.

    6.1k GitHub starsUsed in 1 repo~1.9k tokens
    Business, Finance & HRAuto-check passed

  • Geo Fundamentals

    wasp-lang/wasp

    Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).

    19k GitHub starsUsed in 8 repos~861 tokens
    Marketing & SEOAuto-check passed

  • SEO Geo

    ReScienceLab/opc-skills

    SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.

    1.8k GitHub starsUsed in 4 repos~2.1k tokens
    Marketing & SEOAuto-check passed

  • CCPM Project Management

    automazeio/ccpm

    Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed

More from Ducksss/codex-profiles

  • GitHub Closing Draft

    Ducksss/codex-profiles

    A skill your agent uses when drafting GitHub PRs, issues, listing copy, or maintainer requests for qualified codex-profiles tracker targets.

    177 GitHub stars~913 tokensUpdated yesterday
    Auto-check passed

  • GitHub Lead Gen

    Ducksss/codex-profiles

    A skill your agent uses when running GitHub lead generation for codex-profiles.

    177 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • GitHub Monitoring

    Ducksss/codex-profiles

    A skill your agent uses when reconciling existing GitHub PRs, issues, listings, or outreach-tracker targets for codex-profiles after submission or review.

    177 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about GitHub Lead Qualification

What does GitHub Lead Qualification do?

A skill your agent uses when qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft. GitHub Lead Qualification is an agent skill from Ducksss/codex-profiles. Use when qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft.

When should I use GitHub Lead Qualification?

GitHub Lead Qualification fits situations like: qualifying outreach-tracker GitHub lead candidates for codex-profiles after lead generation and before any closing draft; tasks that involve Lead generation.

How do I install GitHub Lead Qualification in Claude Code?

Run `npx skills add Ducksss/codex-profiles --skill github-lead-qualification -a claude-code`. Or copy the skill folder (.agents/skills/github-lead-qualification in Ducksss/codex-profiles) into .claude/skills/github-lead-qualification in your project. Claude Code loads it when a task matches its description.

How do I install GitHub Lead Qualification in Codex?

Run `npx skills add Ducksss/codex-profiles --skill github-lead-qualification -a codex`. Or copy the skill folder (.agents/skills/github-lead-qualification in Ducksss/codex-profiles) into .agents/skills/github-lead-qualification in your project. Codex loads it when a task matches its description.

Can I use GitHub Lead Qualification in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Ducksss/codex-profiles --skill github-lead-qualification -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-lead-qualification, .gemini/skills/github-lead-qualification, .github/skills/github-lead-qualification and .opencode/skills/github-lead-qualification in your project.

What does GitHub Lead Qualification need to run?

Going by SKILL.md and its folder, GitHub Lead Qualification needs the command-line tools its instructions call (node).

Does GitHub Lead Qualification access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is GitHub Lead Qualification safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does GitHub Lead Qualification use?

GitHub Lead Qualification is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does GitHub Lead Qualification use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 640 tokens, read only when the agent opens those files.

What are the alternatives to GitHub Lead Qualification?

Skills that share tags, products or a category with GitHub Lead Qualification: GitHub Repo Signals (gooseworks-ai/goose-skills, 1.2k stars), Generative Engine Optimization (kostja94/marketing-skills, 1k stars), GitHub Project Contributor Finder API Skill (browser-act/skills, 6.1k stars) and Geo Fundamentals (wasp-lang/wasp, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains GitHub Lead Qualification?

Ducksss (a GitHub user) maintains it in Ducksss/codex-profiles, which has 177 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 6, 2026.

Source: Ducksss/codex-profiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.