CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-debug

Systematic debugging with persistent state across context resets

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-debug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

90%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 content is an exceptionally dense, fully executable operational specification: exact dispatch templates, exact commands, per-outcome handling with validation, re-dispatch caps, and security-conscious data handling throughout. Its only real weaknesses are readability — the compressed run-on paragraphs and heavy indirection to the external workflow file make the sequence effortful to follow — not missing substance.

DimensionReasoningScore

Conciseness

The body is almost purely operational — routing rules, a dispatch task template, exact handling per return header, and commit commands — with zero explanation of concepts Claude already knows and no padding. Every sentence carries instruction weight (e.g. "Stop after 3 re-dispatches, or when two consecutive re-dispatches leave next_action equal to last_next_action"), matching anchor 5 ('Lean and efficient; assumes Claude's competence; every token earns its place').

5 / 5

Actionability

Guidance is fully executable: a literal copy-paste dispatch task template with placeholder semantics, exact commands ("git diff --cached --quiet || git commit -F <message file>", "gsd_run query commit: \"docs(debug): resolve <slug> session\" --files {debug_dir}/resolved/<slug>.md"), and exact first-match-wins handling for all six return headers plus the non-terminal and error cases. This matches anchor 5 ('Fully executable; copy-paste ready code or commands; specific examples cover the common cases').

5 / 5

Workflow Clarity

The loop is a clearly numbered sequence with real validation checkpoints and feedback loops — state-field sanitization for untrusted input, a 3-re-dispatch cap, no-progress detection via last_next_action, blocker reports, and per-header recovery options (e.g. 'Revise fix' re-dispatch after a guardrail rejection). It falls short of anchor 5 because the flow is hard to follow on first read: routing is spread across dense paragraphs, many steps ('run sections 1d, 2 and 3') defer to an external workflow file, and the compact-summary field list ('Session, Root Cause, Fix, Cycles, TDD...') is ambiguous.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), and the single external dependency is one level deep and clearly signaled via the <execution_context> block pointing at gsd-core/workflows/debug.md. Structure is decent — bold section markers (**The loop.**, **Finish.**), numbered loop steps, a routing list — but it uses dense paragraphs rather than clean section headers, so navigation is good rather than easy, matching anchor 4 over anchor 5.

4 / 5

Total

18

/

20

Passed

Description

45%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 names a clear, fairly distinctive niche (stateful debugging across context resets) but is minimal: it lists no concrete capabilities and gives no 'use when' trigger guidance. A user or model relying on it alone would not know when to invoke this skill over a generic debugging skill.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to debug, find a root cause, or fix a bug, especially when a debugging session may span context resets.'

List 2-3 concrete capabilities to raise specificity, e.g. 'Diagnoses root causes, applies fixes (optionally test-first), and checkpoints session state so debugging can resume after a context reset.'

Include natural synonyms users would actually say — bug, error, root cause, failing test, resume session — to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

"Systematic debugging with persistent state across context resets" names the domain (debugging) and one mechanism (persistent state), but lists no concrete actions such as diagnosing root causes, writing failing tests, or committing fixes. This matches anchor 2 ('Names the domain but actions are minimal or generic') rather than anchor 3, since 'persistent state across context resets' describes a property of the skill, not an action it performs.

2 / 5

Completeness

A 'what' is present ("Systematic debugging with persistent state across context resets") but there is no 'Use when...' clause or any equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is above anchor 2 because the 'what' is more than vague — it names the domain and its distinguishing mechanism — but 'when' is entirely missing rather than weakly implied.

3 / 5

Trigger Term Quality

"debugging" is a natural term users would say, and "persistent state" / "context resets" describe the scenario, but common variations and synonyms like "bug", "error", "root cause", "crash", or "failing test" are absent. This fits anchor 3 ('Some relevant keywords but missing common variations or synonyms'), not anchor 4, because there is effectively only one strong natural trigger term.

3 / 5

Distinctiveness Conflict Risk

The phrase "persistent state across context resets" carves out a distinctive niche, but the bare word "debugging" overlaps with any general debugging or bug-fixing skill, and with no explicit trigger guidance nothing separates when this skill should fire instead. This lands on anchor 3 ('Somewhat specific but could still overlap with similar skills') rather than 4, where minor overlap risk would require distinct triggers.

3 / 5

Total

11

/

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-debug/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.