Name: copilot-sdk
Rating: 55.2 (1 reviews)
Author: administrakt0r

copilot-sdk

Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Quality

63%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/copilot-sdk/SKILL.md

The canonical home for this skill is copilot-sdk in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

63%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 highly actionable with executable multi-language examples and a clear core pattern, but it is token-heavy from four-way language duplication and behaves as a monolithic reference rather than an overview pointing to deeper files.

Suggestions

Move the per-language full API references, hooks tables, and MCP config tables into separate files under references/ and link to them from SKILL.md to apply progressive disclosure.

Show one canonical language (e.g. TypeScript) in full per feature and collapse the others into a compact cross-language table or a single reference file to cut duplication.

Remove the redundant Key API Summary section or merge it into the existing per-language examples to recover tokens.

Dimension	Reasoning	Score
Conciseness	Mostly code-driven and assumes programming competence, but repeating full code blocks in all four languages for every feature (plus a duplicated Key API Summary) inflates tokens noticeably.	3 / 5
Actionability	Concrete, copy-paste-ready code is provided in every supported language with config and debug tables; minor gaps like Go's discarded errors keep it just below fully executable.	4 / 5
Workflow Clarity	The 'Core Pattern: Client -> Session -> Message' gives a clear unambiguous sequence, and the debugging section lists failure modes; this is a reference skill so no destructive-operation validation cap applies.	4 / 5
Progressive Disclosure	At ~510 lines everything is inlined in SKILL.md with no bundle files; per-language API references, hooks, and MCP config tables that clearly belong in separate reference files are inline, though section headers provide decent structure.	3 / 5
	Total	14 / 20 Passed

Description

63%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 has strong specificity and a clear distinct niche, but it is purely a 'what' statement with no explicit 'when to use' trigger guidance and limited natural trigger terms.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when building applications that drive GitHub Copilot programmatically, integrating Copilot into tools, or wrapping the Copilot CLI.'

Soften the technical jargon with natural synonyms users would actually say (e.g. 'Copilot automation', 'Copilot API', 'Copilot bot') to broaden trigger-term coverage.

The third-person imperative voice is correct; keep it and avoid drifting into first/second person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'session management, custom tools, hooks, MCP server integration, and streaming' across four named languages — giving comprehensive coverage rather than vague abstractions.	5 / 5
Completeness	It clearly states what the skill does but omits any 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 3 even though the 'what' is strong.	3 / 5
Trigger Term Quality	The only natural user-facing term is 'GitHub Copilot'; the rest ('JSON-RPC', 'MCP server integration', 'session management') is technical jargon, and common natural variations or trigger phrases are absent.	3 / 5
Distinctiveness Conflict Risk	The 'GitHub Copilot SDK' niche wrapping the Copilot CLI via JSON-RPC is mostly distinct, with only minor overlap risk against generic Copilot assistance skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (517 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/copilot-sdk/SKILL.md
Commit: 57c135b

Reviewed: 3 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.