ddaanet/how
skills/how/SKILL.md
Recall procedural knowledge from project decisions. Triggers on "how to do X", step-by-step techniques, or implementation guidance needs. Invoke with "/how <trigger>".
testing
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add ddaanet/agent-core howInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 5, 2026, 2:11 AM25.6s1 file scanned
SKILL.md
- name:
- how
- description:
- Recall procedural knowledge from project decisions. Triggers on "how to do X", step-by-step techniques, or implementation guidance needs. Invoke with "/how <trigger>".
- allowed-tools:
- Bash(edify _recall resolve:*)
- user-invocable:
- true
/how — Procedural Knowledge Recall
Resolve procedural triggers against the memory index. Returns decision file content with ancestor and sibling navigation links.
Resolution Modes
Trigger mode — fuzzy-match an index entry to a decision heading:
edify _recall resolve "how encode paths"
Section mode — look up a heading directly by name (dot prefix):
edify _recall resolve "how .Path Encoding Algorithm"
File mode — load an entire decision file (double-dot prefix, relative to agents/decisions/):
edify _recall resolve "how ..data-processing.md"
When to Use
- Need to know how to accomplish a specific task or technique
- Looking up a step-by-step procedure documented in project decisions
- Need implementation guidance — how to encode paths, how to structure tests, how to configure tools
When NOT to Use
- Need behavioral/situational knowledge — use
/wheninstead - Content already in context from a prior
/recall,/when, or/howinvocation (do not re-resolve) - Exploring unfamiliar code (use Grep/Read directly)
Output Format
Returns the matched section content followed by navigation:
- Broader: ancestor headings and
..file.mdlink for surrounding context - Related: sibling
/howentries under the same parent heading
Related Skills
ddaanet/formalize
development
VerifiedTrustedCommunity
Verify a Python function against its intended behavior by writing an icontract contract and checking it with `edify check` (CrossHair), repairing in a loop. Triggers on "formalize", "verify this function", "add a contract and check it", or after writing a function whose correctness matters. The in-context agent holds intent and asks the user when behavior is ambiguous; CrossHair owns the deduction.
SKILL.mdUpdated Jun 11, 2026
ddaanet/worktree
tools
VerifiedTrustedCommunity
Manage git worktrees for parallel task execution. Triggers on "create a worktree", "set up parallel work", "merge a worktree", "branch off a task", or uses the `wt`, `wt merge`, or `wt-rm` shortcuts. Worktree lifecycle: creation, focused sessions, merge ceremony, cleanup, parallel task setup.
SKILL.mdUpdated Apr 5, 2026
ddaanet/when
testing
VerifiedTrustedCommunity
Recall behavioral knowledge from project decisions. Triggers on "when to do X", situational patterns, or decision content for recognized situations. Invoke with "/when <trigger>".
SKILL.mdUpdated Apr 5, 2026
ddaanet/update
tools
VerifiedTrustedCommunity
Sync edify fragments and portable justfile to match the current plugin version. Detects user-edited files and warns instead of overwriting. Use --force to overwrite conflicts.
SKILL.mdUpdated Apr 5, 2026