Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Xakki/ai-agents-skills/plugin install ai-agents-skillsWrote 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/xakki/ai-agents-skills/skill-import)<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/skill-import"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/skill-import/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/skill-import"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/skill-import.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00126 | $0.00687 |
| Opus 5 | $0.00063 | $0.00344 |
| Sonnet 5 | $0.00025 | $0.00137 |
| Haiku 4.5 | $0.00013 | $0.00069 |
Grade A, and why
skill-import scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-import
Copies skills from configured source repos into <project>/.claude/skills/,
matched to what the project actually needs. Catalog is built on the fly into a
cache; imported skills are tracked for updates.
Set ROOT="${AI_AGENTS_SKILLS_ROOT:-${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT:-${CURSOR_PLUGIN_ROOT:-}}}}". Scripts run via "$ROOT"/skills/skill-import/<script>:
build-catalog.sh, import-skill.sh, update-imported.sh. Config:
sources.tsv (append a row to add a repo). Details, catalog/manifest formats
and the matcher prompt: reference.md.
Modes
| Mode | What it does |
|---|---|
| discover (default) | build catalog → delegate matching to a subagent → present options in the user's language → import chosen |
| update | update-imported.sh [skill|--all] — re-sync imported skills |
| list | show <project>/.claude/skills/.imported.tsv |
| add-source | append a name<TAB>url<TAB>type row to sources.tsv |
Discover (happy path)
- Build/refresh the catalog:
bash "$ROOT"/skills/skill-import/build-catalog.sh(writes${SKILL_IMPORT_CACHE:-~/.cache/skill-import}/catalog.tsv). - Delegate matching to a subagent — do NOT read the full catalog into the
main thread. Hand the subagent the catalog path and the project's doc paths
(
README*,CLAUDE.md/AGENTS.md, stack manifests). It returns a ranked shortlist:skill · source · kind · location · why_relevant(English). See the matcher prompt in reference.md. - Present the shortlist to the user in their language (translate the description + why-relevant). Let them choose.
- Import each chosen skill:
bash "$ROOT"/skills/skill-import/import-skill.sh <source> <skill>(run from the project root, or pass--project <dir>). - The import stages files; commit via the
git-flowskill.
Safety
- Sources are read-only; scripts never push to them.
- Import never overwrites an existing project skill without
--force. - Update never overwrites a differing copy without
--force(shows the diff). - Copy stages only — commits are
git-flow's job.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- build-catalog.sh 3.8 KB runs code
- import-skill.sh 3.9 KB runs code
- reference.md 2.9 KB
- sources.tsv 156 B
- test/build-catalog-hybrid.test.sh 2.4 KB runs code
- test/build-catalog.test.sh 1.1 KB runs code
- test/docs.test.sh 755 B runs code
- test/import-external.test.sh 1.4 KB runs code
- test/import-skill.test.sh 1.5 KB runs code
- test/run-all.sh 250 B runs code
- test/security.test.sh 2.7 KB runs code
- test/update-external.test.sh 3.3 KB runs code
- test/update-imported.test.sh 1.8 KB runs code
- update-imported.sh 2.6 KB runs code
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.
- 11d ago First seen · 49 lines · 126 tokens per session scan A 4591d499035d
skill-import is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 20d ago), licensed MIT. It adds 126 tokens to every session and 687 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
openpanel
Query self-hosted OpenPanel analytics — funnel counts, unique users, breakdowns by os/country/path, raw events. Use whenever analytics numbers are needed: funnel conversion, visitor counts, event counts over a window, period-over-period deltas, "how many signups/checkouts/sessions", or any /darkflow:analytics-review…
taiyi-evolve
A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.
taiyi-diagram-c4
A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
chart-rendering
Render governed Kun charts and tables from structured data for trustworthy comparison and lookup.
legal-risk-assessment
Structure legal-risk reviews by issue, rule source, likelihood, impact, evidence, uncertainty, controls, and escalation.