technical-debt
Process recorded technical debt by identifying safe quick wins first and bundling the highest-value remaining related items into one OpenSpec proposal when…
Skill by spitoglou
Chalk Labs
Need help deploying technical-debt?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/spitoglou-technical-debt
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/technical-debt
What's inside
- Skill name
technical-debt- Description
- Process recorded technical debt by identifying safe quick wins first and bundling the highest-value remaining related items into one OpenSpec proposal when direct fixes are not appropriate.
- License
- MIT
- Instructions
- 109 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Technical Debt Processing Use this workflow when `/process-debt` is invoked or when asked to process recorded debt. ## 1. Read context Read, in order: - `AGENTS.md` - `reports/tech-debt.md` - relevant source files and tests - `reports/registry.md` - `openspec/AGENTS.md` and `openspec/config.yaml` when proposing a change Run `git status --short` before changing files. ## 2. Classify every open item For each open debt item, record: - ID and source report - affected files - user/developer impact - risk of a direct fix - dependencies on other debt - whether an OpenSpec change is required A quick win must be: - small and localized - behaviorally clear - low-risk - independently testable - not a schema, API, auth, synchronization, migration, or architecture change - implementable without changing stated requirements Examples of quick wins include missing tests, isolated validation, documentation, lint fixes, and small defensive fixes. ## 3. Process quick wins For each approved quick win: 1. Add or update tests first where practical. 2. Implement the direct fix. 3. Run: ```bash uv run ruff check app tests uv run pytest --cov=app --cov-report=term-missing -q ``` 4. Require total coverage to remain at least 85%. 5. Mark the debt item resolved in `reports/tech-debt.md`, preserving its source and resolution date. 6. Add a concise entry to `reports/registry.md` if a report or meaningful fix was produced. Do not create an OpenSpec change for a qualifying quick win. ## 4. If no quick wins are suitable Select the highest-value related open items by considering: 1. Critical/security/data-integrity impact 2. Blocking future synchronization or migration work 3. Number of related items that can be solved together 4. User impact and risk reduction 5. Implementation feasibility Bundle related items into one OpenSpec proposal. Do not create multiple overlapping proposals. Use: ```bash openspec new change <kebab-case-name> ``` Then complete the `spec-driven` artifacts in order: ```text proposal → specs → design → tasks ``` The proposal must include: - bundled debt IDs and source reports - motivation and measurable value - scope and non-goals - migration and rollback strategy - external-integration compatibility impact - security/reliability considerations - test and coverage plan Validate the proposal before finishing: ```bash openspec status <change> openspec validate <change> ``` Do not implement the proposal unless the user separately asks to apply it. ## 5. Final report Summarize: - debt items reviewed - quick wins fixed and tests added - remaining debt - proposal created, if any - verification results and final coverage
From spitoglou/pi-project-workflows, MIT.
More from spitoglou/pi-project-workflows
- 0.521score
code-review
spitoglou
Perform a structured code review for correctness, security, performance, maintainability, migrations, UI behavior, and test coverage.
SkillBFreshness: BClaude Code +9 - 0.518score
ci
spitoglou
Run a Python project's local quality gate with UV, including Ruff, tests, coverage, and optional security checks.
SkillBFreshness: BClaude Code +9 - 0.516score
rfc
spitoglou
Create or review an RFC for major calendar features, schema changes, API changes, external integrations, or architecture decisions.
SkillBFreshness: BClaude Code +9 - 0.516score
release
spitoglou
Prepare a safe release for a UV-managed Python application with checks, changelog guidance, versioning, and explicit confirmation before Git operations.
SkillBFreshness: BClaude Code +9 - 0.516score
architecture-review
spitoglou
Assess application architecture, API boundaries, database schema evolution, integration design, and maintainability for substantial changes.
SkillBFreshness: BClaude Code +9 - 0.516score
agent-coordination
spitoglou
Coordinate Pi-native review, architecture, security, CI, release, RFC, and technical-debt workflows using reports and registries instead of Claude subagents.
SkillBFreshness: BClaude Code +9 - 0.516score
security-review
spitoglou
Review applications for OWASP risks, unsafe input handling, secret exposure, dependency issues, database problems, and future external-integration risks.
SkillBFreshness: BClaude Code +9 - 0.513score
incident-review
spitoglou
Produce a blameless postmortem for application incidents, data issues, failed migrations, or integration failures.
SkillBFreshness: BClaude Code +9 - 0.513score
database-migrations
spitoglou
Use this workflow for SQLite schema changes, migrations, event persistence, categories, or synchronization tables.
SkillBFreshness: BClaude Code +9 - 0.483score
test-coverage
spitoglou
Run and improve the project's Python test suite while preserving the required minimum of 85 percent coverage.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 7, 2026 (2 months ago)
- Last release
- Aug 7, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from spitoglou
- 0.521score
code-review
spitoglou
Perform a structured code review for correctness, security, performance, maintainability, migrations, UI behavior, and test coverage.
SkillBFreshness: BClaude Code +9 - 0.518score
ci
spitoglou
Run a Python project's local quality gate with UV, including Ruff, tests, coverage, and optional security checks.
SkillBFreshness: BClaude Code +9 - 0.516score
rfc
spitoglou
Create or review an RFC for major calendar features, schema changes, API changes, external integrations, or architecture decisions.
SkillBFreshness: BClaude Code +9 - 0.516score
release
spitoglou
Prepare a safe release for a UV-managed Python application with checks, changelog guidance, versioning, and explicit confirmation before Git operations.
SkillBFreshness: BClaude Code +9 - 0.516score
architecture-review
spitoglou
Assess application architecture, API boundaries, database schema evolution, integration design, and maintainability for substantial changes.
SkillBFreshness: BClaude Code +9 - 0.516score
agent-coordination
spitoglou
Coordinate Pi-native review, architecture, security, CI, release, RFC, and technical-debt workflows using reports and registries instead of Claude subagents.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get technical-debt running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
technical-debt skill. Agent Mart. https://agentmart.dev/skills/spitoglou-technical-debt (last updated 2026-10-24)