← All creators

PsychQuant

Organization

Claude Code 的長期記憶 — 在 ~/.claude/projects 逐字記錄之上的可拋棄索引與可插拔記憶策略(全本機)

27 indexed · 0 Featured · 0 stars · avg score 69
Prolific

Categories

Indexed Skills (27)

AI & Automation Listed

spectra-audit

Audit changed code for security sharp edges — dangerous defaults, type confusion, and silent failures

0 Updated 2 weeks ago
PsychQuant
AI & Automation Listed

spectra-debug

Systematically debug a problem using a four-phase workflow

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-discuss

Have a focused discussion about a topic and reach a conclusion

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-drift

Detect drift between a Spectra change and the current codebase state

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-ingest

Update an existing Spectra change from external context

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-propose

Create a change proposal with all required artifacts

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-analyze

Analyze artifact consistency for a change

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-apply

Implement or resume tasks from a Spectra change

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-archive

Archive a completed change

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-ask

Query openspec/documents and answer questions

0 Updated 2 weeks ago
PsychQuant
Code & Development Listed

spectra-commit

Commit files related to a specific Spectra change

0 Updated 2 weeks ago
PsychQuant
Testing & QA Listed

spectra-verify

Verify implementation matches artifacts

0 Updated 2 weeks ago
PsychQuant
AI & Automation Listed

ltm-setup

Use when claude-code-ltm is not yet usable — the user just installed the plugin, a `ltm_query` call came back with `索引不存在` / `indexMissing`, the user asks "how do I set this up", "為什麼查不到", "ltm 要怎麼開始用", "要先做什麼嗎", or wants to rebuild the index after an upgrade. Checks binary and index state, explains the one-time cost, and runs `ltm build` with the user's consent.

0 Updated 4 days ago
PsychQuant
AI & Automation Listed

ltm-recall

Use when the user refers to something from a past Claude Code conversation on this machine — "我們之前討論過…", "那次量測的數字是多少", "為什麼當初決定…", "上次那個 bug 怎麼修的" — or whenever answering would require knowing what was decided in an earlier session. Searches the local transcript corpus and returns pointers to the original turns.

0 Updated 4 days ago
PsychQuant
AI & Automation Listed

spectra-audit

Audit changed code for security sharp edges — dangerous defaults, type confusion, and silent failures

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-debug

Systematically debug a problem using a four-phase workflow

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-discuss

Have a focused discussion about a topic and reach a conclusion

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-drift

Detect drift between a Spectra change and the current codebase state

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-ingest

Update an existing Spectra change from external context

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-propose

Create a change proposal with all required artifacts

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-apply

Implement or resume tasks from a Spectra change

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-archive

Archive a completed change

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-ask

Query openspec/documents and answer questions

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-commit

Commit files related to a specific Spectra change

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-analyze

Analyze artifact consistency for a change

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

spectra-verify

Verify implementation matches artifacts

0 Updated 3 weeks ago
PsychQuant
AI & Automation Listed

pacing-playbook

Use BEFORE launching multiple agents, fanning out subagents, running a Workflow, batching parallel tasks, or designing any multi-agent / parallel orchestration. Encodes the anti-burst pacing discipline that prevents triggering Anthropic's acceleration-limit / short-burst throttle (429, and 529 "Server is temporarily limiting requests · not your usage limit"). Trigger whenever about to fan out, open several workflows, or chain agent launches back-to-back.

0 Updated 4 days ago
PsychQuant

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.