| Skill | Added | Review |
|---|---|---|
resolve-repo devflow-plugin/skills/resolve-repo/SKILL.md Resolve the correct repository for a task — detect VCS platform, match ticket to repo, clone if missing. Run this in a sub-agent to avoid filling main context. | 62 62 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
resolve-repo skills/resolve-repo/SKILL.md Resolve the correct repository for a task — detect VCS platform, match ticket to repo, clone if missing. Run this in a sub-agent to avoid filling main context. | 58 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
retain-learning devflow-plugin/skills/retain-learning/SKILL.md Retain a new learning, discovery, or hard-won insight into Hindsight so it's available in future sessions. | 63 63 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
retain-learning skills/retain-learning/SKILL.md Retain a new learning, discovery, or hard-won insight into Hindsight so it's available in future sessions. | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
review devflow-plugin/skills/review/SKILL.md Use when reviewing a PR/MR by URL or the local working-tree diff — runs multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence) with confidence scoring and optional draft inline comments on the MR. Triggers for `/devflow:review` or any "review this PR/MR" request. | 71 71 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
review-document devflow-plugin/flows/review/skills/review-document/SKILL.md Use when reviewing a prose document — KB article, RFC, spike, runbook, PRD, design doc, knowledge-base page — hosted on Google Docs, Confluence, a local file path, or an arbitrary URL. Checks correctness, internal consistency, audience-fit, prose clarity, and external-claim verification; cross-checks against existing platform comments to avoid re-flagging; returns severity-tagged findings with anchor + quote + concrete fix. Use when asked to "review this doc / KB / RFC / spike / runbook / PRD" and the target is prose, not a code diff. Counterpart to the write-spike skill. NOT for code diffs — use /devflow:review for those. | 76 76 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
review-document skills/review-document/SKILL.md Use when reviewing a prose document — KB article, RFC, spike, runbook, PRD, design doc, knowledge-base page — hosted on Google Docs, Confluence, a local file path, or an arbitrary URL. Checks correctness, internal consistency, audience-fit, prose clarity, and external-claim verification; cross-checks against existing platform comments to avoid re-flagging; returns severity-tagged findings with anchor + quote + concrete fix. Use when asked to "review this doc / KB / RFC / spike / runbook / PRD" and the target is prose, not a code diff. Counterpart to the write-spike skill. NOT for code diffs — use /devflow:review for those. | 76 76 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
review-document devflow-plugin/skills/review-document/SKILL.md Use when reviewing a prose document — KB article, RFC, spike, runbook, PRD, design doc, knowledge-base page — hosted on Google Docs, Confluence, a local file path, or an arbitrary URL. Checks correctness, internal consistency, audience-fit, prose clarity, and external-claim verification; cross-checks against existing platform comments to avoid re-flagging; returns severity-tagged findings with anchor + quote + concrete fix. Use when asked to "review this doc / KB / RFC / spike / runbook / PRD" and the target is prose, not a code diff. Counterpart to the write-spike skill. NOT for code diffs — use /devflow:review for those. | 76 76 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
review devflow-plugin/flows/review/skills/review/SKILL.md Use when reviewing a PR/MR by URL or the local working-tree diff — runs multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence) with confidence scoring and optional draft inline comments on the MR. Triggers for `/devflow:review` or any "review this PR/MR" request. | 75 75 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
review skills/review/SKILL.md Use when reviewing a PR/MR by URL or the local working-tree diff — runs multi-perspective parallel agents (bug scanner, CLAUDE.md compliance, test coverage, plan alignment, git history, sibling MR/epic coherence) with confidence scoring and optional draft inline comments on the MR. Triggers for `/devflow:review` or any "review this PR/MR" request. | 75 75 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
session-summary devflow-plugin/skills/session-summary/SKILL.md Generate a session summary for Langfuse tracing — capture what happened, decisions made, and metrics for observability. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
session-summary skills/session-summary/SKILL.md Generate a session summary for Langfuse tracing — capture what happened, decisions made, and metrics for observability. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
spec-feature devflow-plugin/skills/spec-feature/SKILL.md Spec a new feature — recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
spec-feature skills/spec-feature/SKILL.md Spec a new feature — recall architecture knowledge, create a spec document, build an implementation plan, and break into tasks. | 57 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
task-complete devflow-plugin/skills/task-complete/SKILL.md Mark a devflow task as done — update status, move to done/ folder, and retain learnings. | 57 57 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
task-complete skills/task-complete/SKILL.md Mark a devflow task as done — update status, move to done/ folder, and retain learnings. | 60 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
task-prioritize devflow-plugin/skills/task-prioritize/SKILL.md Reprioritize a devflow task — move between priority folders (P0-P4) and update frontmatter. | 58 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
task-prioritize skills/task-prioritize/SKILL.md Reprioritize a devflow task — move between priority folders (P0-P4) and update frontmatter. | 56 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: bd4b70c | |
trace-review devflow-plugin/skills/trace-review/SKILL.md Use when asked to review skill telemetry, find week-over-week skill regressions, run a weekly Langfuse trace report, or check whether a skill got slower / more expensive / more error-prone - produces a per-skill regression report from the local Langfuse trace store and can schedule itself. | 72 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c | |
trace-review skills/trace-review/SKILL.md Use when asked to review skill telemetry, find week-over-week skill regressions, run a weekly Langfuse trace report, or check whether a skill got slower / more expensive / more error-prone - produces a per-skill regression report from the local Langfuse trace store and can schedule itself. | 72 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: bd4b70c |