SDD Observatory
Stars
176.1K
Contributors
3
Open issues
189
Age
5 months
Last push
yesterday
Latest release
v1.1.0 Jul 8, 2026
Week of Jul 19, 2025: 0 commits Week of Jul 26, 2025: 0 commits Week of Aug 2, 2025: 0 commits Week of Aug 9, 2025: 0 commits Week of Aug 16, 2025: 0 commits Week of Aug 23, 2025: 0 commits Week of Aug 30, 2025: 0 commits Week of Sep 6, 2025: 0 commits Week of Sep 13, 2025: 0 commits Week of Sep 20, 2025: 0 commits Week of Sep 27, 2025: 0 commits Week of Oct 4, 2025: 0 commits Week of Oct 11, 2025: 0 commits Week of Oct 18, 2025: 0 commits Week of Oct 25, 2025: 0 commits Week of Nov 1, 2025: 0 commits Week of Nov 8, 2025: 0 commits Week of Nov 15, 2025: 0 commits Week of Nov 22, 2025: 0 commits Week of Nov 29, 2025: 0 commits Week of Dec 6, 2025: 0 commits Week of Dec 13, 2025: 0 commits Week of Dec 20, 2025: 0 commits Week of Dec 27, 2025: 0 commits Week of Jan 3, 2026: 0 commits Week of Jan 10, 2026: 0 commits Week of Jan 17, 2026: 0 commits Week of Jan 24, 2026: 0 commits Week of Jan 31, 2026: 5 commits Week of Feb 7, 2026: 3 commits Week of Feb 14, 2026: 1 commit Week of Feb 21, 2026: 1 commit Week of Feb 28, 2026: 1 commit Week of Mar 7, 2026: 3 commits Week of Mar 14, 2026: 3 commits Week of Mar 21, 2026: 3 commits Week of Mar 28, 2026: 1 commit Week of Apr 4, 2026: 0 commits Week of Apr 11, 2026: 5 commits Week of Apr 18, 2026: 5 commits Week of Apr 25, 2026: 30 commits Week of May 2, 2026: 10 commits Week of May 9, 2026: 5 commits Week of May 16, 2026: 6 commits Week of May 23, 2026: 3 commits Week of May 30, 2026: 15 commits Week of Jun 6, 2026: 9 commits Week of Jun 13, 2026: 19 commits Week of Jun 20, 2026: 7 commits Week of Jun 27, 2026: 68 commits Week of Jul 4, 2026: 38 commits Week of Jul 11, 2026: 13 commits
Commits per week, last 12 months · 254 total

Metrics updated Jul 18, 2026 · collected automatically from the GitHub API

Core approach

Deliberately anti-pipeline: the README names Spec Kit and BMAD as approaches that "own the process" at the cost of user control, and offers small, hackable, composable skills instead. The core primitive is grilling — walk the plan's decision tree one question at a time, each question paired with a recommended answer, reading the codebase for anything it can settle itself. Two front doors wrap it: grill-me (stateless, leaves no artifacts) and grill-with-docs (writes a CONTEXT.md ubiquitous-language glossary and sparing ADRs as terms and decisions resolve), feeding a spec → tickets → implement chain the user drives step by step.

Workflow

  1. /setup-matt-pocock-skills — one-time per-repo config: issue tracker (GitHub, Linear, or local files), triage labels, doc locations
  2. /grill-me or /grill-with-docs — one-question-at-a-time interview down the plan's decision tree; the docs variant captures terms into CONTEXT.md and hard-to-reverse decisions into ADRs inline
  3. /to-spec — synthesize the settled conversation into a spec (problem, user stories, seams, out-of-scope) and publish it to the tracker, without re-interviewing
  4. /to-tickets — split the spec into tracer-bullet vertical-slice tickets, each declaring its blocking edges
  5. /implement — build the tickets via red-green-refactor TDD at the pre-agreed seams, then run /code-review (standards + spec axes) and commit
  6. /wayfinder — optional upstream step for efforts too big for one session: chart a map of investigation tickets first

Supported tools

Strengths

  • Small, composable, editable skills instead of a phase-gated pipeline — the user keeps control of the process and can debug it
  • One question at a time with a recommended answer each; questions the codebase can settle are answered by reading, not asking
  • grill-with-docs leaves durable in-repo artifacts — a CONTEXT.md glossary and sparing ADRs — building a DDD-style ubiquitous language that cuts agent verbosity
  • Tracer-bullet vertical-slice tickets with explicit blocking edges, so several agents can work the frontier in parallel
  • Explosive adoption (176k+ stars within six months) and two install philosophies: hackable copies via skills.sh, or a managed Claude Code plugin

Limitations

  • Deliberately not turnkey — you orchestrate the chain yourself, and the interview-driven flow demands sustained human attention per change
  • The engineering chain needs per-repo setup (tracker, triage labels, doc locations) before to-spec and to-tickets work
  • Specs and tickets publish to the issue tracker rather than versioning in-repo — only the glossary and ADRs live in the tree, so spec-to-code drift is hard to observe
  • Young and fast-moving under a single maintainer, with skills still being deprecated and reshaped (deprecated/ and in-progress/ directories in-tree)

Notes

The grill-me family is the explicit counter-position to the pipelines tracked elsewhere in this observatory: its README argues that frameworks like Spec Kit and BMAD help by owning the process, but in doing so take away control and make process bugs hard to fix. Its bet is the opposite — that alignment (via the grilling interview) matters more than artifacts, and that the durable in-repo record should be a vocabulary (CONTEXT.md) and decision log (ADRs) rather than regenerable specs, which it publishes to the issue tracker as coordination artifacts instead. Unusually for the category, the repo dogfoods its own method: an .agents/ directory, in-tree ADRs, and changeset-driven releases.

Added Jul 18, 2026 · Assessment last reviewed Jul 18, 2026 · How we track