Add doubt-driven-development skill#139
Merged
addyosmani merged 3 commits intoaddyosmani:mainfrom May 9, 2026
Merged
Conversation
Codifies adversarial fresh-context review as an in-flight development posture, distinct from /review (post-hoc PR-level verdict). Every non-trivial decision passes through a 5-step cycle (CLAIM → EXTRACT → DOUBT → RECONCILE → STOP) before standing. Cross-model escalation is described as a contract, not as hardcoded CLI invocations — the skill instructs the agent to ask the user which external tool to use and how, since CLI syntax (Gemini, Codex, etc.) changes and varies by environment. Updates README skill listing (count, Build table, project tree), CLAUDE.md Skills by Phase, and using-agent-skills flowchart + Quick Reference for discoverability parity with the existing skills.
federicobartoli
force-pushed
the
feat/doubt-driven-development
branch
3 times, most recently
from
64d2b05 to
940f932
Compare
Folds in the safety and consistency findings surfaced by running the skill against itself in two cycles (single-model adversarial review + cross-model verification via Codex). Cross-model escalation is now offered in every interactive cycle, and the CLI invocation path uses a read-only sandbox with prompts piped through stdin to neutralize shell-escaping and prompt-injection risks (verified against Codex 0.128.0 and Gemini 0.41.2 locally). Internal consistency fixes from the adversarial self-review: the adversarial prompt explicitly overrides persona templates; the persona roster is referenced rather than duplicated; the Step 2 'Claim' bullet is renamed Assertion to disambiguate from the Step 1 CLAIM block; the manual fallback in Loading Constraints is labeled as a degraded last-resort path; the forward reference to Step 3 is anchored; the Verification checklist no longer contains an item not derivable from the Process; and using-agent-skills's Lifecycle Sequence now includes the skill at position 7.
federicobartoli
force-pushed
the
feat/doubt-driven-development
branch
from
940f932 to
97e12d0
Compare
Resolves README.md conflict by taking main's wording ("entry points.
The pack includes 21 skills total") and Meta section, both landed in
PR addyosmani#142 while this PR was open. The doubt-driven-development row in
the Build table and the directory tree entry auto-merged cleanly.
Owner
|
Really enjoyed reading this one. The "in-flight posture, not post-hoc verdict" part is what makes the whole skill click, and you held the line on it cleanly. Especially the bits explaining how doubt-driven differs from Going to merge as-is - if anything wobbles in practice I'll follow up with a polish PR, but you've done the careful version of this and I don't want to nitpick it. Thanks for the patience on the review queue. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds a
doubt-driven-developmentskill: an in-flight adversarial-review posture distinct from post-hoc gates like/review. Every non-trivial decision passes through CLAIM → EXTRACT → DOUBT → RECONCILE → STOP, bounded at three cycles before escalating to the user.Why a skill (not a command, not a persona)
/reviewand thecode-reviewerpersona produce PR-level verdicts after the artifact has congealed. This skill catches wrong directions while course-correction is still cheap. The naming follows the*-driven-developmentconvention already established in this repo (TDD, SDD) — methodology, not tooling. Orchestration sits in the main session, respectingreferences/orchestration-patterns.md(personas don't invoke other personas).The repo currently has no skill covering in-flight verification of non-trivial decisions:
code-review-and-qualityis post-hoc, andsource-driven-developmentverifies framework facts rather than the author's reasoning about the artifact. This skill fills that gap.Cross-model escalation
Optional, user-authorized, designed safety-first:
/loop, scheduled runs. External CLIs are never invoked without explicit authorization.codex exec --sandbox read-onlyandgemini --approval-mode plan, both verified against local installs (Codex 0.128.0, Gemini 0.41.2). The artifact under review may itself contain prompt-injection.-p "...". Artifacts routinely contain backticks and$(...); shell interpolation is unsafe.Test evidence
Applied the skill to its own commits as the integration test:
gemini --approval-mode plan -p "" < prompt.md) was verified locally so the SKILL.md example is a working command, not a guess; Gemini was not used as a second reviewer.Files changed
skills/doubt-driven-development/SKILL.md— new skillREADME.md— table entry and skill descriptionskills/using-agent-skills/SKILL.md— discovery flowchart, quick reference, and Lifecycle Sequence position 7CLAUDE.md— listed under Build phase