skill-copilot-provider

GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-copilot-provider/SKILL.md

Quality

Content

57%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-sectioned, actionable provider reference with concrete detection, auth, and dispatch commands. Its weaknesses are padding (emoji indicators, output mockups), an implicit rather than explicit workflow with no validation steps, and no progressive disclosure — everything lives inline in a single file with one dangling out-of-bundle reference.

Suggestions

Cut or compress the "Provider Indicators" legend and "Example Workflows" sections into a brief note or a separate reference file — they display output mockups rather than instruct, which would raise conciseness toward 4-5.

Make the workflow explicit and validated: a numbered sequence (detect → verify auth with a cheap test prompt → dispatch) with a checkpoint like `copilot -p "ping" --no-ask-user` to confirm authentication before use.

Fix the detection snippet so it is standalone-executable (use `exit 0` or wrap in a function) and move detail content (indicator legend, workflow examples) into a `references/` file linked from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is a mostly efficient sectioned reference, but the "Provider Indicators" emoji legend and two "Example Workflows" ASCII mockups mostly illustrate what output looks like rather than instruct, and the legend duplicates the block above it. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim profile of level 4.	3 / 5
Actionability	Concrete, mostly executable commands appear throughout: `command -v copilot`, `copilot login`, `export COPILOT_GITHUB_TOKEN="github_pat_..."`, and `copilot -p "<prompt>" --no-ask-user`, plus a PAT setup URL and permission name. Minor gaps keep it at 4: the detection snippet's bare `return 0` only runs inside a sourced function, and there is no worked example showing a real prompt and its parsed output.	4 / 5
Workflow Clarity	The section order (Detection → Authentication → Dispatch) and the explicit auth precedence list imply a sequence, but the steps are never sequenced explicitly and no validation checkpoints exist (e.g. verifying auth or a test prompt after setup). This matches 'sequence present but checkpoints missing or implicit' rather than level 4's clearly sequenced steps.	3 / 5
Progressive Disclosure	Sections are well-organized, but the ~159-line body has no bundle files, and content that would fit a reference file (indicator legend, example workflow mockups) is inlined; the sole cross-reference (`skills/blocks/codex-host-adapter.md`) points outside the bundle. This matches 'some structure but could be better organized; content that should be separate is inline' rather than level 4's mostly-appropriate placement with clear references.	3 / 5
	Total	13 / 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 is terse and distinct, naming a concrete integration mechanism, but it functions as a technical label rather than a capability description. It lacks any "Use when..." trigger guidance and natural user phrasing, capping completeness and trigger quality at mid-scale.

Suggestions

Add an explicit 'Use when' clause, e.g. "Use when the user asks to use GitHub Copilot, needs a free research provider, or mentions Copilot CLI" — this would lift completeness from 3 toward 4-5.

Include natural trigger terms and synonyms users would actually say ("GitHub Copilot", "Copilot subscription", "free/zero-cost research provider") instead of only jargon like "copilot -p programmatic mode".

State the concrete capability in third person (e.g. "Dispatches research and exploration prompts to GitHub Copilot CLI via `copilot -p` programmatic mode") so the 'what' reads as actions rather than a role label.

Dimension	Reasoning	Score
Specificity	The description names the domain ("GitHub Copilot CLI as optional zero-cost provider") and one concrete mechanism ("via copilot -p programmatic mode"), but enumerates no actions beyond that single integration path. It matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the several-action list of level 4.	3 / 5
Completeness	The 'what' is stated (Copilot as an optional zero-cost provider via `copilot -p`), but there is no "Use when..." clause or equivalent trigger guidance, which the rubric caps at 3. This matches 'clear what but when is missing or only weakly implied'.	3 / 5
Trigger Term Quality	Terms like "GitHub Copilot CLI", "copilot -p", and "programmatic mode" include the natural keyword "GitHub Copilot", but the phrasing is jargon-heavy and misses common variations users would say (e.g. "use Copilot", "Copilot subscription", "research provider"). Some relevant keywords are present, matching level 3 rather than the good coverage of level 4.	3 / 5
Distinctiveness Conflict Risk	"GitHub Copilot CLI" and "copilot -p" form a clear, distinct niche unlikely to trigger the wrong skill, though it could overlap with sibling provider skills in the same multi-LLM ecosystem. This is 'mostly distinct; minor overlap risk with closely related skills' rather than the fully distinct trigger-phrase set of level 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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: nyldn/claude-octopus
Path: skills/skill-copilot-provider/SKILL.md
Commit: 0093dab

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.