CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

manage-experiments

Create, update (metrics, dates, description, hypothesis, baseline/comparison treatments, status), or delete Harness FME feature-flag experiments. Delegates metric selection to choose-metric, metric creation to create-metric, event wiring to instrument-metric, results to review-experiment-results, flag/definition prep to create-feature-flag and update-flag-targeting. Use when asked to create, modify, pause, resume, complete, or delete an experiment. Do not use for explaining results (review-experiment-results). Trigger phrases: create experiment, set up A/B test, design experiment, launch test, update experiment, pause/resume/complete experiment, delete experiment.

Quality

91%

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

88%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 high-quality operational skill: the workflows are unambiguous with explicit confirmation and verification checkpoints, error codes map to concrete recovery actions, and commands are copy-paste ready. The main improvements are trimming repetition (the CLI rule/name limitation is stated three times) and moving more of the inline operational detail into bundle reference files.

Suggestions

State the CLI limitation on updating `rule`/`name` once (e.g. in a single 'CLI gaps' note) instead of three times in Create Step 6, Update Step 2, and the Troubleshooting table.

Move the Troubleshooting table and the traffic-readiness field checks into a references/ file linked from the relevant steps, keeping SKILL.md closer to an overview-plus-workflow and reducing inline tokens.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational detail (exact params, error-code semantics, CLI gaps) and assumes Claude's competence rather than explaining concepts, fitting the 4 anchor 'efficient; minor instances of over-explanation'. Not 5 because some content is repeated: the CLI limitation on changing `rule`/`name` appears in Create Step 6, Update Step 2, and the Troubleshooting table, and a few compound sentences could be tightened.

4 / 5

Actionability

Fully executable guidance: exact MCP invocations ("harness_update · fme_experiment · params: { experiment_id } · body: { description?, hypothesis?, ... }"), copy-paste-ready CLI commands ("harness update experiment <experiment-id> --set description=foo --set status=PAUSED"), concrete constraints (name 2-250 chars, hypothesis max 500 chars, "Do not send assignmentSource (400 if present)"), and error-specific recovery actions. Matches the 5 anchor: specific commands cover the common cases.

5 / 5

Workflow Clarity

The 8-step create flow is clearly sequenced with explicit validation checkpoints ("**STOP HERE.** Wait for explicit confirmation"; Step 8 compares every field against the approved draft and stops on mismatch) and error-recovery feedback loops (409 → ask for a new name, 404 → back to Step 1). The destructive delete flow requires stricter confirmation and offers a safer alternative, satisfying the destructive-operation validation requirement.

5 / 5

Progressive Disclosure

Good structure: the one bundle file (references/stop-conditions.md) is real, well-signaled, contextually linked from the right steps, and one level deep; bulk detail (tool-map, write-safety, concepts) lives in separate repo-level reference files. Falls short of 5 because the SKILL.md itself is a long operational manual with some content (traffic-readiness field checks, troubleshooting rows duplicating in-body guidance) that could be split into a reference file.

4 / 5

Total

18

/

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 names the exact domain and lifecycle operations with field-level specificity, answers both 'what' and 'when' explicitly, and carves out a distinct niche with delegation routing and an exclusion clause. The only weakness is slightly incomplete natural-language trigger coverage (a few common phrasings like 'archive experiment' are absent).

DimensionReasoningScore

Specificity

"Create, update (metrics, dates, description, hypothesis, baseline/comparison treatments, status), or delete Harness FME feature-flag experiments" enumerates multiple concrete actions with per-operation field detail, plus delegation targets (choose-metric, create-metric, instrument-metric). It is comprehensive for the domain, fitting the 5 anchor better than 4 ('minor gaps in coverage') since every lifecycle operation and its updatable fields are named.

5 / 5

Completeness

Both 'what' (create/update/delete with field-level detail and delegation) and 'when' are explicitly answered: "Use when asked to create, modify, pause, resume, complete, or delete an experiment" plus concrete trigger phrases and an explicit exclusion ("Do not use for explaining results (review-experiment-results)"). This clearly matches the 5 anchor: both questions answered with concrete trigger phrases.

5 / 5

Trigger Term Quality

"Trigger phrases: create experiment, set up A/B test, design experiment, launch test, update experiment, pause/resume/complete experiment, delete experiment" gives good natural-language coverage with synonyms. It falls short of the 5 anchor because a few natural variations are missing (e.g. "archive experiment", "A/B test on a flag", "feature flag experiment"), but is well above 3's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

"Harness FME feature-flag experiments" establishes a clear niche, and explicit delegation routing plus "Do not use for explaining results (review-experiment-results)" minimizes overlap with closely related sibling skills. The 4 anchor's 'minor overlap risk with closely related skills' is addressed by the explicit boundaries, so 5 fits best.

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: 24 suspicious

Warning

Total

15

/

16

Passed

Repository

harness/harness-ai

Path

plugins/claude/skills/manage-experiments/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.