hoa-introspect
Produce an evidence-cited, cross-agent self-report with deterministic usage facets and a rigorously bounded blind-spot audit. Use only when explicitly asked for "my usage insights", "audit my work patterns", "where am I wasting effort", "blind spots", or a periodic "self-retro". Do not use for raw records or cross-agent search, a single-session summary, qualifying findings into approved assets (use hoa-introspect-distill), or direct skill creation (use hoa-skill-work). Heavyweight and explicit-invocation-only; never invoke as a side effect of another skill.
Target: Search & knowledge management. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- hoa-introspect
- Contract
- Workflow
- Guardrails
- Bounded-mode wording
- Output shape
Turn a bounded set of agent-history records into a layered self-report: L1 — usage panorama: hard, reproducible counts produced only by scripts/aggregate.py. L2 — blind-spot audit: a small set of re-checkable qualitative findings, or explicitly none when evidence does not support one. This is a reflective analysis, not a personality assessment. It describes observable work patterns within the supplied coverage only. Input. Prefer a manifest-first Retrieval Bundle in the consumed schema (hoa's prompts/cross-agent-history-retrieval.md can produce one). Without one, work in bounded mode: accept only user-provided paths or records directly accessible in this runtime. Say exactly what that restriction excludes. Read the minimal consumed schema before parsing. Output. Produce all of the following: 1. facets JSON (aggregateddata and facetssummary) created by scripts/aggregate.py; 2. shareable HTML and Markdown reports written only after scripts/piigate.py permits their target; 3. a short, redacted at-a-glance chat summary. Report language. Default to en-US. Honor reportlanguage only from untracked configuration, or an explicit agent instruction. Render all L1/L2 narrative and headings in
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- wxxb789/hoa
- Source file
- skills/hoa-introspect/SKILL.md
- Fixed revision
- beb1eca66d8fed7c3942dc3ef50990bf37837706
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明，再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: wxxb789/hoa · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-09T20:02:15.408Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.