一键导入
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Detect and track technical debt from conversation and PR review comments. Resurface in weekly retros, promote to commitments when ready to fix.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when adding or reviewing tests for Reborn behavior — choosing a test tier, covering a bug fix, testing model/tool-choice behavior, touching tests/integration or tests/fixtures/llm_traces, or when a test needs Postgres, Docker, or a live LLM.
Navigate building a user-facing feature in the Reborn stack (a capability that crosses product_workflow → composition → webui_v2 → runtime/serve → frontend). Use when planning or implementing any new Reborn settings page, endpoint, facade method, or runtime-backed capability — especially before writing code, to avoid rebuilding what already exists and to wire it in one pass instead of layer-by-layer.
Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.
Generate or update the IronClaw architecture overview video using Remotion. Use when asked to update, regenerate, or modify the architecture video, add/remove scenes, or reflect codebase changes in the video.
Use when writing or reviewing a change in crates/ that adds a trait, a crate, a dependency edge, a re-export, or code in ironclaw_reborn_composition — or when deciding whether an abstraction, layer, or crate boundary is justified in the IronClaw Reborn stack.
Use when starting work in the IronClaw repo, deciding where a feature/fix/prompt/doc belongs, tracing how a request flows, looking up which crate owns a subsystem, or when repo docs, the knowledge graph, or component names seem stale, missing, or contradictory.
| name | tech-debt-tracker |
| version | 0.1.0 |
| description | Detect and track technical debt from conversation and PR review comments. Resurface in weekly retros, promote to commitments when ready to fix. |
| activation | {"keywords":["tech debt","technical debt","hack","hacky","refactor later","fixme","workaround","shortcut","should refactor","bandaid","temporary fix","show tech debt","debt backlog"],"patterns":["(?i)(this|that) is (a |kind of )?(hack|workaround|bandaid|band-aid|shortcut|kludge)","(?i)(we |I )should (refactor|clean up|rewrite|fix) (this|that) (later|eventually|someday)","(?i)(show|list|review) (tech )?debt","(?i)add.*tech ?debt"],"tags":["commitments","developer","tech-debt"],"max_context_tokens":1200} |
Track technical debt from conversation and PR review comments. Debt items live in projects/commitments/tech-debt/ and are resurfaced weekly.
When the user says something implying tech debt ("this is a hack but it works", "we should really refactor the auth module", "adding another TODO"), silently extract it.
Action:
memory_search in projects/commitments/tech-debt/.projects/commitments/tech-debt/<slug>.md:---
type: tech-debt
detected_at: <today YYYY-MM-DD>
repo: <current repo context if known, else null>
severity: <high|medium|low>
category: <refactor|performance|security|testing|documentation|architecture>
source: conversation
source_pr: null
---
# <Brief title>
<What the debt is and why it exists.>
## Context
<What prompted the shortcut — deadline, complexity, missing knowledge.>
## Proposed fix
<What a proper fix would look like, if discussed.>
Severity rules:
high: security shortcuts, data integrity risks, architectural violationsmedium: code quality, missing tests, poor abstractionslow: style issues, minor workarounds, documentation gapsDo NOT interrupt conversation flow.
When the triage mission processes recently merged PRs, it should scan review comments for tech-debt patterns:
For each match, create a tech-debt item with source: pr-review and source_pr: owner/repo#123.
User says: "add tech debt: the caching layer needs TTL eviction."
Write directly to projects/commitments/tech-debt/, confirm briefly.
User says: "show tech debt" or "debt backlog"
Action:
memory_tree("projects/commitments/tech-debt/", depth=1) — list files (skip README.md)memory_read each for title, severity, detected_at, repo, source## Tech Debt Backlog
### High Severity
- **<title>** (repo: <repo>, <N> days old, source: <conversation|PR #X>) — <category>
### Medium Severity
- ...
### Low Severity
- ...
---
<count> total. <count> chronic (30+ days).
Say "resolve <title>" to mark fixed, or "promote <title>" to create a commitment.
For large items, use `/plan <description>` to create a structured fix plan.
User says: "resolved the caching TTL debt"
Move to projects/commitments/resolved/ with original type preserved. Confirm.
User says: "let's fix the auth refactor" or "promote the caching debt"
Create commitment in projects/commitments/open/ with tags: [tech-debt] and resolution_path: agent_can_handle if it's a code task. For complex items, suggest: "This looks like a multi-step refactor. Use /plan <description> to create a structured fix plan."
Slugify: lowercase, hyphens, max 50 chars. Prefix with repo slug if known:
nearai-ironclaw-auth-refactor.mdcaching-ttl-eviction.md