Save Skill
Save the current conversation insight as a reusable skill in the knowledge repo
Install
$ agentstack add skill-theaichimera-claude-code-project-intelligence-save-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-theaichimera-claude-code-project-intelligence-save-skill) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/save-skill - Save a Skill from This Session
Save a piece of knowledge, pattern, or workflow from the current conversation as a reusable skill that will be injected into future sessions.
Usage
The user invokes /save-skill to save a skill. If no name is given, infer a kebab-case name from the content.
Instructions
When the user invokes /save-skill:
- Identify the content to save. Look at the recent conversation context:
- If the user just said "save that as a skill" or similar, use the most recent substantive assistant response
- If the user provides specific content or instructions, use that
- If unclear, ask the user what they want to save
- Determine the project. Use the current working directory's project name (basename of CWD).
- Format as a skill file with YAML frontmatter:
---
name:
project:
generated:
sessions: []
confidence: high
source: manual
---
#
- Write the file to:
~/.claude/knowledge//skills/.mdCreate the directory if it doesn't exist (mkdir -p).
- Commit and push to the knowledge repo:
cd ~/.claude/knowledge && git add -A && git commit -m "Add skill: for " && git push- Confirm to the user what was saved and where.
Guidelines
- Skills should be actionable instructions, not observations. "When X happens, do Y" not "X was observed."
- Keep skills focused — one pattern/workflow per skill
- Use numbered steps for procedures, bullet points for checklists
- Include context about why this pattern matters (e.g., "This avoids the 20x cost estimation error we hit before")
- If a skill with the same name already exists, update it (merge new insights with existing content)
Examples
/save-skill— Save the last discussed pattern (auto-name it)/save-skill deployment-checklist— Save as "deployment-checklist"/save-skillafter user says "that debugging approach was great, remember it" — Capture the approach
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: theaichimera
- Source: theaichimera/claude-code-project-intelligence
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.