sdd-triage
Skill3 starsChanged 36 days agoMITView on GitHub
SDD triage that recommends to the human the process level for a feature, fix, or refactoring request — full SDD, lean SDD, or spot change — from risk signals with evidence, before any artifact exists. Use when starting sdd-orchestrate-flow on a feature without a checkpoint or when asked whether a request is worth the SDD flow. Don't use for resuming a feature with a checkpoint or for slicing a broad request into several PRDs (use sdd-orchestrate-prds).
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-ready-fixSkill
- ai-ready-scoreSkill
- architectural-analysisSkill
- commitSkill
- deep-reviewSkill
- domain-modelingSkill
- dotnet-efficient-validationSkill
- herdr-orchestrationSkill
- no-workaroundsSkill
- repository-cli-efficiencySkill
- sdd-create-prdSkill
- sdd-create-techspecSkill
- sdd-execute-correctionsSkill
- sdd-execute-taskSkill
- sdd-orchestrate-flowSkill
- sdd-orchestrate-prdsSkill
- sdd-orchestrate-tasksSkill
- sdd-plan-auditSkill
- sdd-plan-correctionsSkill
- sdd-plan-refactoringSkill
- sdd-plan-tasksSkill
- sdd-review-codeSkill
- sdd-snapshotSkill
- update-nuget-packagesSkill
- writing-agents-mdSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Gather signals: Read AGENTS.md for critical areas, risk skills, and commands.
- Very specific: line 32
Output: every signal filled with evidence or not measured.
- Very specific: line 52
Deliver: Commit only when asked, through the commit skill.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Triage a request for SDD
Triage spends little to avoid spending a lot: it gathers signals with evidence, applies a rubric, and recommends a level; the human decides. Budget: up to ten targeted searches or reads, with no build or tests. Triage that needs more than that to understand the request already points to sdd-full.
| Level | Path |
sdd-full | sdd-orchestrate-flow with every gate |
sdd-lean | sdd-orchestrate-flow with a short PRD (problem, RF with acceptance, out of scope), HIL 1 and HIL 2 merged into one decision, a plan of one or two tasks, and independent review kept |
spot | The spot branch of this skill, outside SDD |
- Understand. Extract the type (feature, fix, refactoring), the primary outcome, and the expected behavior. With an existing checkpoint for the request, stop and resume through
sdd-orchestrate-flow. With more than one primary outcome, recommendsdd-fullthroughsdd-orchestrate-prdsand go to step 4. Output: request with one identified primary outcome, or a resume or slicing referral. Gather signals. Read
AGENTS.mdfor critical areas, risk skills, and commands. Locate the likely change points through the repository's context graph when it has one (e.g.graft ask,graft callers <symbol> --depth 2), or by direct search. Fill each signal withpath:lineevidence ornot measured:Signal Question S1 Public contract Does it change what a consumer sends or receives: an API or MCP surface, a serialized DTO, a schema or database script, a file format, or configuration? Documentation-only text (description, example, grouping) counts as absent. S2 Critical area Does it touch an area that AGENTS.mddeclares critical or that requires a risk skill (e.g. credentials, provider authentication, payments)?S3 Concurrency Does it involve a transaction, lock, idempotency, queue, background polling, or shared state? S4 Blast radius How many production files, modules, and transitive callers change behavior? S5 Open decision Is there an ambiguous requirement or an unanswered product decision? S6 Obligations How many distinct observable behaviors does the request require? S7 Tests Do tests exercise the behavior, or does a direct regression test fit? S8 Reversibility Does it persist data, migrate state, or trigger an external action that is hard to undo? Output: every signal filled with evidence or
not measured.- Recommend. Apply the rubric, whose thresholds are a starting point calibrated by the triage log:
sdd-fullwhen any holds: S1, S2 with a behavior change, S5, S8, S6 above three obligations, or S4 across more than one module.spotwhen all hold: one module, up to three production files, none of S1, S2, S3, S5, or S8, an unambiguous expected behavior, and a feasible regression test (S7).sdd-leanotherwise. Anot measuredsignal that would decide the level counts as present. Output: rubric level with the deciding signals.
- HIL 0. Present the level the rubric recommends, the deciding signals with evidence, and what each level costs in artifacts, HILs, and review. Ask with the available question tool, recommended option first. Silence keeps the decision pending. With
--mode auto, do not ask: the rubric level is the decision, recorded as autonomous, and the protocol in.agents/skills/sdd-orchestrate-flow/references/autonomous-mode.mdapplies from here on. Append one line totasks/triage-log.jsonlwith date, summarized request, signals, rubric level, and human decision, orautonomousin auto mode. Output: level decided by the human and recorded. - Continue.
sdd-fullandsdd-leanreturn tosdd-orchestrate-flow, passing on--modeand--log-decisionswhen supplied, and the flow records the triage as a decision inworkflow.md; forsdd-lean, also record the merge of HIL 1 and HIL 2 as a change to the stops.spotfollows the branch below. Output: next step started on the decided path.
Spot branch
- Implement. Make the smallest coherent change with a regression test that fails before and passes after, or a behavior test when there is no defect. Validate with the repository's validation skills. Output: change applied and test result recorded before and after.
- Tripwire. Stop and return to step 2 with the new evidence when the diff exceeds the file limit decided at HIL 0 (default: three production files), touches S1, S2, S3, or S8, or a product decision appears. The change stays in the worktree as evidence; discarding it is a human decision. Output: diff confirmed within the limit, or triage reopened with the new evidence.
- Review. Review the diff with the repository's review skill or the host's native review. Output: review findings fixed or taken to the human.
- Deliver. Commit only when asked, through the
commitskill. Output: delivery in the requested state, with the regression test and review as evidence.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

