tech-debt-tracker

Detect and track technical debt from conversation and PR review comments. Resurface in weekly retros, promote to commitments when ready to fix.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/tech-debt-tracker/SKILL.md

Quality

Content

76%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 lean, highly actionable, and well-organized with a copy-paste template and concrete tooling, but its batch (PR scan) and semi-destructive (resolve/move) modes lack the validation checkpoints needed to score higher on workflow clarity.

Suggestions

Add a dedup/validation step to Mode B's batch PR scan (e.g. memory_search before writing each item) to mirror Mode A's duplicate check.

Insert a verify-before-move checkpoint in Mode E (confirm the source item exists, then move to resolved/) to guard the destructive relocation.

Optionally split the listing display template or severity/category reference into a short reference file to lift progressive_disclosure toward 5, though inline is acceptable at this length.

Dimension	Reasoning	Score
Conciseness	Lean body that assumes Claude knows what tech debt is and avoids concept explanation; minor instances of detail that could be trimmed (e.g. the full listing display template), keeping it just below the 'every token earns its place' anchor 5.	4 / 5
Actionability	Provides a copy-paste-ready markdown template with full frontmatter, concrete tool calls (memory_search, memory_tree, memory_read), explicit severity/category enums, and concrete slugify filename examples — fully actionable guidance covering common cases.	5 / 5
Workflow Clarity	Modes A and D have clear sequences and Mode A includes a duplicate-check checkpoint, but Mode B is a batch PR scan with no dedup/validation step and Mode E moves files to resolved/ without verifying the item exists first; the batch/destructive cap at 3 applies.	3 / 5
Progressive Disclosure	A single self-contained file organized into clearly headed sections (Modes A–F, filename conventions) with no need for external references; good structure with minor organization gaps, just above the 'could be better organized' anchor 3.	4 / 5
	Total	16 / 20 Passed

Description

58%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 conveys a clear, multi-action purpose and a distinct niche, but lacks an explicit 'Use when…' trigger clause and only carries the single natural keyword 'technical debt', omitting the synonyms users actually say.

Suggestions

Add an explicit 'Use when…' clause naming concrete triggers, e.g. 'Use when the user mentions tech debt, hacks, workarounds, TODOs, or refactor-later comments, or when reviewing PRs for deferred work.'

Broaden trigger terms to include natural synonyms users say (hack, workaround, TODO, refactor later, bandaid, shortcut) rather than only 'technical debt'.

Keep the lifecycle actions but consider one concrete output cue (e.g. 'writes items to the tech-debt backlog') to sharpen the 'what' further.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions across the debt lifecycle — 'Detect and track', 'Resurface in weekly retros', 'promote to commitments' — naming the domain (conversation and PR review comments); not quite the exhaustive, granular action list of anchor 5.	4 / 5
Completeness	Has a clear 'what' (detect/track/resurface/promote) but no explicit 'Use when…' clause — the 'when' is only weakly implied via source contexts, so per guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains the core natural term 'technical debt' and 'PR review comments' but misses common synonyms users actually say (hack, workaround, TODO, refactor later, bandaid); relevant keywords present, common variations missing.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (technical debt tracking) with specific sources, mostly distinct from other skills with only minor overlap risk against general commitments/tracking skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nearai/ironclaw
Path: skills/tech-debt-tracker/SKILL.md
Commit: 9102166

Reviewed: ~16 hours 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.