CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-discuss-phase

Gather phase context through adaptive questioning before planning.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./pi/package-skills/gsd-discuss-phase/SKILL.md
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.

The body is an effective, disciplined dispatcher: fully executable routing with fail-closed error handling, explicit lazy-loading of one-level-deep workflow files, and no wasted explanation. Its only real weaknesses are mild redundancy between the summary and delegated workflows, and a dense inline bash shim-resolver that would be cleaner as a bundled script.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence and never explains known concepts; the dense bash blob is runtime-necessary rather than padding. Minor trimming is possible (the 6-step summary overlaps the delegated workflow files, and the 'do not pre-load' admonition appears twice), so anchor 4 rather than 5.

4 / 5

Actionability

Guidance is fully executable: a copy-paste-ready bash resolver with fallback chain and remediation message, exact workflow file paths, a deterministic if/elif/else routing covering --assumptions, DISCUSS_MODE=assumptions, and the default, plus explicit fail-closed dispatch error handling — matching the top anchor.

5 / 5

Workflow Clarity

Sequence is clear (resolve tools → query DISCUSS_MODE → route → read workflow file end-to-end → lazy-load templates) with validation checkpoints (tool identity verification, fail-closed dispatch handling) and a success_criteria checklist. It falls short of 5 because the deeper checkpoints (exploring each area 'until satisfied') are delegated to external workflow files rather than validated here.

4 / 5

Progressive Disclosure

References are well-signaled and one level deep (discuss-phase.md, discuss-phase-assumptions.md, list-phase-assumptions.md, templates/context.md, discuss-phase-power.md) with explicit lazy-loading rules, and sections (objective, execution_context, context, process, success_criteria) are well organized. Minor gap: the ~15-line inline bash resolution blob is hard to read and would fit better in a script file, so anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

53%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.

The description states a clear, third-person purpose but is minimal: it conveys the what without any explicit when-to-use guidance, capping completeness at 3. Trigger terms are domain-appropriate yet sparse, missing the natural variations users would type.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting the discussion step of a phase, when the user wants to clarify gray areas or lock in decisions before planning."

Expand the capability list to concrete actions: identifying gray areas, deep-diving user-selected topics, and writing {phase_num}-CONTEXT.md with locked decisions.

Include natural synonyms users would type — "discuss phase", "clarify decisions", "gray areas", "CONTEXT.md" — to improve trigger term coverage.

DimensionReasoningScore

Specificity

"Gather phase context through adaptive questioning" names the domain and one concrete action with a mechanism and timing ("before planning"), but offers only that single action and remains fairly abstract, matching anchor 3 rather than 4's 'several specific actions'.

3 / 5

Completeness

The "what" is clear (gather phase context via adaptive questioning), but there is no "Use when..." clause or equivalent explicit trigger guidance — "before planning" only weakly implies when, which caps this dimension at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Terms like "phase context", "questioning", and "planning" are relevant to the domain, but natural phrases a user would say ("discuss the phase", "clarify decisions", "gray areas") and their variations are absent, fitting anchor 3 rather than 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"Gather phase context through adaptive questioning before planning" carves a fairly distinct niche in a phase-based workflow suite with minimal conflict against generic skills, but adjacent skills in the same suite (planning, requirements phases) could overlap since no distinct trigger phrases are given — anchor 4, not 5.

4 / 5

Total

13

/

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

open-gsd/gsd-core

Path

pi/package-skills/gsd-discuss-phase/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.