CtrlK
BlogDocsLog inGet started
Tessl Logo

working-with-skills

Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Use whenever you are about to call any `skill-*` tool, asked to author or edit a shared skill, or troubleshoot why a skill write was rejected. Pairs with `skills-store` (which covers the raw tool surface) by adding the decision-tree, efficiency, and pitfall guidance.

71

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable, well-structured meta-skill with concrete examples for every tool and a solid concurrency workflow. Minor gains remain in de-duplicating the path/file_path guidance and splitting long example blocks into bundled reference files.

Suggestions

De-duplicate the `path` vs `file_path` rule: keep it in 'File-path parameter naming' and reduce the Common pitfalls bullet to a one-line pointer rather than restating the full rule.

Move the full per-tool JSON call examples (skill-create, skill-update variants, file CRUD) into a `references/examples.md` and have the body route to it, shrinking the body toward the skill's own ~500-line guidance.

Add an explicit post-write verification step to the update workflow (e.g. re-`skill-get` to confirm the change landed) so destructive/batch writes have a checkpoint beyond base_version.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's familiarity with MCP/skills, with every section earning its place; the only trim opportunity is the `path` vs `file_path` guidance repeated both in its own section and again in Common pitfalls.

4 / 5

Actionability

Every tool gets a copy-paste-ready JSON call example (skill-list, skill-get, skill-create, skill-update with edits/file_edits, skill-file-create/delete/rename, skill-archive) covering the common cases.

5 / 5

Workflow Clarity

A clear decision tree plus sequenced update/porting steps and a real concurrency feedback loop (409 -> re-get -> reconcile -> retry with base_version) is present, though routine writes lack an explicit post-write verification checkpoint.

4 / 5

Progressive Disclosure

Sections are well-organized with no nested references, but the 394-line monolithic body inlines extensive per-tool JSON examples that could be split into references/ files, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

92%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, trigger-rich description that clearly answers what and when and explicitly distinguishes itself from the adjacent skills-store skill. The only minor gap is breadth of synonyms/file-extension triggers.

DimensionReasoningScore

Specificity

"how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files" lists multiple concrete actions with comprehensive coverage of the skill-management lifecycle.

5 / 5

Completeness

It states what the skill does (discover/read/create/update/refactor skills) and gives an explicit "Use whenever..." clause with concrete trigger scenarios, satisfying both what and when.

5 / 5

Trigger Term Quality

"about to call any `skill-*` tool", "asked to author or edit a shared skill", and "troubleshoot why a skill write was rejected" are natural user phrases, but synonym/extension coverage is thinner than the anchor-5 example.

4 / 5

Distinctiveness Conflict Risk

"Pairs with `skills-store` (which covers the raw tool surface) by adding the decision-tree, efficiency, and pitfall guidance" carves out a clear niche and actively disambiguates from the sibling skill.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 11 missing

Warning

Total

15

/

16

Passed

Repository
PostHog/posthog
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.