CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

custom-investigation

Run a custom investigation: review a chosen slice of conversations instead of a random sample, by writing a SQL selector over the observed agent's telemetry, and optionally narrow what the reviewer reports. Use when a message asks to investigate only certain conversations -- ones that hit an error, used a particular tool, ran slowly, mention a topic, looped, or were abandoned -- or asks to re-review conversations already seen with a different focus. Covers the telemetry table a selector reads, writing the selector, previewing what it matched, and starting the run.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

The body is a well-structured, highly actionable guide for a multi-tool workflow: exact tool calls and arguments, explicit validation gates and error-recovery loops, and per-source detail correctly deferred to one-level-deep reference files. Its only weakness is mild repetition and discursiveness in a few sections (the link rule and the reviewer-fence discussion).

DimensionReasoningScore

Conciseness

The body is dense with deployment-specific knowledge Claude cannot already know (refusal semantics, the three-attempt cap, preview/run sampling divergence, quota and billing effects, insight-recency side effects), with no generic concept explanations. Minor over-explanation remains: the link rule is stated three ways ("no exceptions" heading, "every time", "Never list the examples as plain text") and the reviewer-fence discussion is somewhat discursive. Efficient with minor trimmable instances -- anchor 4, not 5, and well above the "unnecessary explanation" of anchor 3.

4 / 5

Actionability

Fully executable guidance throughout: exact tool names (`describe_telemetry`, `preview_custom_investigation`, `start_custom_investigation`, `get_investigation`, `list_investigations`) with exact argument names (`selector_sql`, `review_focus`, `session_review_focus`, `@window_start`), a copy-paste markdown bullet template for examples, and exact SQL forms including the `AI.IF` signature with the `__AI_MODEL__` placeholder. As an instruction-only skill its guidance is concrete and actionable, matching the top anchor.

5 / 5

Workflow Clarity

A 7-step numbered workflow with an explicit validation checkpoint chain (preview, show matches, get approval, then start) and thorough feedback loops: fix-and-repreview on rejection, a hard stop after `attempts_exhausted`, narrowing on `timed_out`, and re-validation at start. This batch operation has explicit validation and error-recovery, matching the top anchor.

5 / 5

Progressive Disclosure

The bundle has three one-level-deep reference files (big_query.md, cloud_logging.md, cloud_ops.md), one per telemetry source, and the body correctly keeps source-specific recipes out of SKILL.md. Navigation is well signaled: load `selector_recipes` via `load_skill_resource` and "Load only that file: the other references describe other telemetry sources." Clear overview, appropriate split, easy navigation -- matches the top anchor.

5 / 5

Total

19

/

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 description: it states concrete capabilities in third person, gives an explicit "Use when" clause with specific triggering scenarios, and is clearly distinguishable from sibling skills. Trigger-term coverage is good though not exhaustive of natural synonyms.

Suggestions

Add a few natural synonym phrases users might say (e.g., "failed", "stuck in a loop", "slow sessions") to the trigger clause for broader keyword coverage.

DimensionReasoningScore

Specificity

Names multiple concrete actions -- "review a chosen slice of conversations instead of a random sample", "writing a SQL selector over the observed agent's telemetry", "narrow what the reviewer reports", "previewing what it matched", and "starting the run" -- with comprehensive coverage of the skill's capabilities. This matches the comprehensive anchor; it goes beyond the score-4 example, which lists fewer actions.

5 / 5

Completeness

Explicitly answers both questions: the what is concrete (SQL selector over telemetry, optional reviewer narrowing) and the when is an explicit "Use when a message asks to investigate only certain conversations ... or asks to re-review conversations already seen with a different focus" with concrete trigger conditions. Clearly matches the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrasings -- "hit an error", "used a particular tool", "ran slowly", "mention a topic", "looped", "abandoned", "re-review" -- giving good keyword coverage. Not 5 because common synonyms and variations (e.g., "failed", "stuck", "slow conversations") are missing; not 3 because coverage clearly exceeds "some relevant keywords".

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (custom investigation of agent telemetry via SQL selectors versus a random ambient sweep) with distinct triggers like "re-review conversations already seen with a different focus". Minimal conflict risk with generic review or analysis skills.

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

google/adk-samples

Path

core/python/ambient-quality-agent/src/ambient_quality_agent/skills/custom-investigation/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.