CtrlK
BlogDocsLog inGet started
Tessl Logo

auditing-the-fleet

The fleet-wide audit — sweep every agent, mine recent sessions for failures/anomalies, classify root causes, and branch a DRAFT proposal per fix (never freeze/promote); write a report to memory. Load when asked to audit all agents or what's underperforming.

72

Quality

88%

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

77%

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

The body is a highly actionable, well-sequenced orchestration playbook with strong validation guardrails, though it is somewhat verbose and relies on external skill playbooks rather than its own reference files for progressive disclosure.

Suggestions

Trim restated guardrails (e.g. consolidate the 'propose, don't dispose / no promotes' rule from the defaults section and the scope guard) to reduce token cost without losing clarity.

If detailed taxonomies or report templates belong to this skill, split them into one-level-deep reference files under references/ and link them from the body; otherwise note explicitly that the deep material lives in the named companion skills.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining concepts Claude already knows, but it is long and includes some restatement (e.g. 'No promotes, ever — propose, don't dispose' repeated alongside the scope guard) that could be tightened.

2 / 3

Actionability

Concrete, named tools and exact paths throughout — `posthog__agent-applications-sessions-list`, `new-draft-create` with `source_revision_id`, `memory-write` to `reports/fleet-audit/latest.md` — giving copy-paste-ready guidance rather than abstraction.

3 / 3

Workflow Clarity

A clearly numbered 1–6 sweep with explicit validation checkpoints (`validate-create`, 'Stop here. No freeze, no promote.'), a feedback loop (fix or drop on failed validation), and a budgeted triage guard for the destructive/batch operation of editing the whole fleet.

3 / 3

Progressive Disclosure

Sections are well-organized, but detailed playbooks live in other skills (`debugging-sessions`, `editing-agents-safely`) referenced inline without bundle files here, so there are no real one-level-deep reference files in this skill to navigate; structure is present but not the anchored cross-file pattern.

2 / 3

Total

10

/

12

Passed

Description

100%

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

The description is specific, uses third person, and pairs concrete actions with an explicit trigger clause covering both 'what' and 'when'. It occupies a clear niche with natural trigger phrasing.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'sweep every agent', 'mine recent sessions for failures/anomalies', 'classify root causes', 'branch a DRAFT proposal per fix' — matching the anchor that lists multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both 'what' (sweep/classify/branch a DRAFT/write a report) and 'when' via the 'Load when asked to audit all agents or what's underperforming' trigger clause.

3 / 3

Trigger Term Quality

Natural user-facing terms like 'audit my fleet' and 'what's underperforming' are echoed as explicit triggers, giving good coverage of phrases a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The fleet-wide audit niche is narrow and paired with distinctive triggers ('audit my fleet', 'what's underperforming'), making conflict with other single-agent skills unlikely.

3 / 3

Total

12

/

12

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

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.