CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

promote

Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement. Use when the user runs /si:promote or asks to make a learned behavior permanent.

71

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is promote in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable workflow skill: the seven-step process is clearly sequenced with user-confirmation checkpoints around destructive edits, and supporting tables and templates make the guidance concrete. Weaknesses are minor — a redundant Tips section and a dubious MEMORY_DIR path computation.

Suggestions

Fix or simplify the MEMORY_DIR computation in Step 2 — the chained sed expressions produce an inconsistent path encoding; either use a single well-defined encoding or instruct Claude to locate the memory directory directly.

Trim the Tips section to only novel advice (e.g., keep the quarterly-review tip) and drop points that restate rules already given in Step 4's distillation rules and Step 5's 200-line guidance.

Add a brief verification step after writing to the target (e.g., re-reading the edited file or section to confirm the rule landed under the correct heading), strengthening the feedback loop for the write operation.

DimensionReasoningScore

Conciseness

The body is largely lean — the before/after distillation example, decision-guide tables, and templates all earn their place — but the Tips section repeats three rules already stated in Steps 4–5 ("Keep CLAUDE.md under 200 lines", "One rule per line", "Include the concrete command"), which is minor padding.

4 / 5

Actionability

Provides concrete grep commands, a rules frontmatter template, an output confirmation template, and a scope-to-target mapping table. However, the MEMORY_DIR bash computation ("pwd | sed 's|/|%2F|g; s|%2F|/|; s|^/||'") is convoluted and yields a suspect mixed-encoding path, so not every command is reliably executable.

4 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit validation checkpoints: matching entries are confirmed with the user in Step 2, and the destructive MEMORY.md edit in Step 6 requires user confirmation before removal. The promote/don't-promote decision guide adds a checklist, matching the top anchor.

5 / 5

Progressive Disclosure

The skill is self-contained with no bundle files and no inlined content that belongs in separate files; sections are well organized and easy to navigate, which per the rubric's simple/self-contained guidance merits the top score.

5 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it precisely states the transformation with concrete sources, targets, and purpose, and gives an explicit, natural 'Use when' trigger clause anchored by the command name. Only minor gaps in action enumeration and trigger synonyms keep it from full marks.

DimensionReasoningScore

Specificity

The description concretely names the source ("auto-memory (MEMORY.md)"), both destinations ("CLAUDE.md or .claude/rules/"), and the outcome ("for permanent enforcement"), but only states one composite action rather than enumerating several specific actions, so it sits between the 3 and 4 anchors — noticeably above the midpoint.

4 / 5

Completeness

Explicitly answers both what ("Graduate a proven pattern from auto-memory (MEMORY.md) to CLAUDE.md or .claude/rules/ for permanent enforcement") and when ("Use when the user runs /si:promote or asks to make a learned behavior permanent") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes the concrete command trigger ("/si:promote") and natural phrases like "make a learned behavior permanent" and "promote", but misses common user variations such as "always do this", "remember this", or "enforce this rule".

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (memory-to-rules promotion) with distinct artifacts (MEMORY.md, CLAUDE.md, .claude/rules/) and a named command, so the risk of triggering for the wrong skill is minimal.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

alirezarezvani/claude-skills

Path

.gemini/skills/promote/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.