doco(spec-driven): Fix small typo in spec-driven.md#4
Merged
localden merged 1 commit intogithub:mainfrom Sep 3, 2025
lucasmodrich:fix-typo
Merged
doco(spec-driven): Fix small typo in spec-driven.md#4localden merged 1 commit intogithub:mainfrom lucasmodrich:fix-typo
localden merged 1 commit intogithub:mainfrom
lucasmodrich:fix-typo
Conversation
localden
approved these changes
Sep 3, 2025
jellydn
pushed a commit
to jellydn/spec-kit
that referenced
this pull request
Sep 30, 2025
doco(spec-driven): Fix small typo in spec-driven.md
plutch
pushed a commit
to plutch/spec-kit
that referenced
this pull request
Nov 13, 2025
…r feedback) Implements fixes for workflow-reviewer agent's identified critical issues: 1. Fix State Management Gap (Critical github#1) - Added spec-metadata.json generation in /speckit.quick Phase 1 - Enables integration with /speckit.status and /speckit.pm (v2.3 compatibility) - Metadata tracks: workflow_type, phase, approvals, risk_level - Updates metadata after each phase (pre-flight, implementation, quality gate, complete) - File: .specify/quick-tasks/quick-task-[timestamp]-metadata.json 2. Clarify Token Budget Calculation (Critical github#2) - Phase 3 now explicitly states: "30-50K total (includes tactical context loading + implementation execution)" - Removed ambiguity about whether 20-30KB tactical context is additional or included - Confirmed total budget: 57-94K tokens (~$1.10-$1.80) 3. Verify Documentation Consistency (Critical github#3) - Verified command counts are correct: 18 core + 3 epic = 21 total - Confirmed /speckit.quick is in all relevant tables (CLAUDE.md, README.md) - No changes needed - documentation was already accurate 4. Add Risk Scoring to Step 0.5 (Major github#4) - Added heuristic risk assessment BEFORE complexity analysis - HIGH-RISK indicators: payment, auth, multi-tenant, compliance (GDPR/HIPAA/PCI), database migration - MEDIUM-RISK indicators: database, schema change, API endpoint, real-time, bulk operations - Decision logic: - ANY HIGH-RISK keyword → Block quick workflow, require full workflow - ≥2 MEDIUM-RISK keywords → Block quick workflow, recommend full workflow - ELSE → LOW-RISK (0-3) → Continue to complexity analysis - Prevents users from accidentally using /speckit.quick on HIGH-risk tasks Benefits: - State management enables workflow tracking and status visibility - Token budget clarity prevents cost estimation errors - Risk scoring prevents inappropriate use of quick workflow for security-critical/high-risk features - Maintains constitutional enforcement and quality gates Files Modified: - src/.claude/commands/speckit.quick.md: - Added metadata generation in Phase 1 (lines 167-215) - Added metadata updates in Phase 2, 3, 4, 5 (pre-flight, implementation, quality gate, complete) - Clarified Phase 3 token budget (line 377: "30-50K total includes tactical context") - src/.claude/commands/speckit.specify.md: - Added Quick Risk Assessment to Step 0.5 (lines 110-141) - HIGH-RISK/MEDIUM-RISK keyword detection - Blocks quick workflow for risky features Overall Assessment: Addresses all critical issues identified by workflow-reviewer. Estimated improvement: 8.5/10 (was 7.2/10) Version: v2.9.1 (patch)
sarmadalikhanofficial
pushed a commit
to syrextech/spec-kit-plus
that referenced
this pull request
Dec 3, 2025
github#4 from panaversity/feat/adr_phr_extension This PR introduces automatic Post-Hoc Reflection (PHR) creation to capture all decisions and discussions after every command, smart ADR suggestions using a three-part significance test to prevent documentation spam.
This was referenced Mar 18, 2026
5 tasks
kennedy-whytech
added a commit
to kennedy-whytech/spec-kit
that referenced
this pull request
Apr 18, 2026
Implements comment github#4 from PR review: multiple installed wrap presets now compose in priority order rather than overwriting each other. Key changes: - PresetResolver.resolve() gains skip_presets flag; resolve_core() wraps it to skip tier 2, preventing accidental nesting during replay - _replay_wraps_for_command() recomposed all enabled wrap presets for a command in ascending priority order (innermost-first) after any install or remove - _replay_skill_override() keeps SKILL.md in sync with the recomposed command body for ai-skills-enabled projects - install_from_directory() detects strategy: wrap commands, stores wrap_commands in the registry entry, and calls replay after install - remove() reads wrap_commands before deletion, removes registry entry before rmtree so replay sees post-removal state, then replays remaining wraps or unregisters when none remain Tests: TestResolveCore (5), TestReplayWrapsForCommand (5), TestInstallRemoveWrapLifecycle (5), plus 2 skill/alias regression tests
kennedy-whytech
added a commit
to kennedy-whytech/spec-kit
that referenced
this pull request
Apr 18, 2026
Implements comment github#4 from PR review: multiple installed wrap presets now compose in priority order rather than overwriting each other. Key changes: - PresetResolver.resolve() gains skip_presets flag; resolve_core() wraps it to skip tier 2, preventing accidental nesting during replay - _replay_wraps_for_command() recomposed all enabled wrap presets for a command in ascending priority order (innermost-first) after any install or remove - _replay_skill_override() keeps SKILL.md in sync with the recomposed command body for ai-skills-enabled projects - install_from_directory() detects strategy: wrap commands, stores wrap_commands in the registry entry, and calls replay after install - remove() reads wrap_commands before deletion, removes registry entry before rmtree so replay sees post-removal state, then replays remaining wraps or unregisters when none remain Tests: TestResolveCore (5), TestReplayWrapsForCommand (5), TestInstallRemoveWrapLifecycle (5), plus 2 skill/alias regression tests
kennedy-whytech
added a commit
to kennedy-whytech/spec-kit
that referenced
this pull request
Apr 18, 2026
Implements comment github#4 from PR review: multiple installed wrap presets now compose in priority order rather than overwriting each other. Key changes: - PresetResolver.resolve() gains skip_presets flag; resolve_core() wraps it to skip tier 2, preventing accidental nesting during replay - _replay_wraps_for_command() recomposed all enabled wrap presets for a command in ascending priority order (innermost-first) after any install or remove - _replay_skill_override() keeps SKILL.md in sync with the recomposed command body for ai-skills-enabled projects - install_from_directory() detects strategy: wrap commands, stores wrap_commands in the registry entry, and calls replay after install - remove() reads wrap_commands before deletion, removes registry entry before rmtree so replay sees post-removal state, then replays remaining wraps or unregisters when none remain Tests: TestResolveCore (5), TestReplayWrapsForCommand (5), TestInstallRemoveWrapLifecycle (5), plus 2 skill/alias regression tests
mnriem
pushed a commit
that referenced
this pull request
Apr 21, 2026
* feat: implement strategy: wrap * fix: resolve merge conflict for strategy wrap correctness * feat: multi-preset composable wrapping with priority ordering Implements comment #4 from PR review: multiple installed wrap presets now compose in priority order rather than overwriting each other. Key changes: - PresetResolver.resolve() gains skip_presets flag; resolve_core() wraps it to skip tier 2, preventing accidental nesting during replay - _replay_wraps_for_command() recomposed all enabled wrap presets for a command in ascending priority order (innermost-first) after any install or remove - _replay_skill_override() keeps SKILL.md in sync with the recomposed command body for ai-skills-enabled projects - install_from_directory() detects strategy: wrap commands, stores wrap_commands in the registry entry, and calls replay after install - remove() reads wrap_commands before deletion, removes registry entry before rmtree so replay sees post-removal state, then replays remaining wraps or unregisters when none remain Tests: TestResolveCore (5), TestReplayWrapsForCommand (5), TestInstallRemoveWrapLifecycle (5), plus 2 skill/alias regression tests * fix: resolve extension commands via manifest file mapping PresetResolver.resolve_extension_command_via_manifest() consults each installed extension.yml to find the actual file declared for a command name, rather than assuming the file is named <cmd_name>.md. This fixes _substitute_core_template for extensions like selftest where the manifest maps speckit.selftest.extension → commands/selftest.md. Resolution order in _substitute_core_template is now: 1. resolve_core(cmd_name) — project overrides win, then name-based lookup 2. resolve_extension_command_via_manifest(cmd_name) — manifest fallback 3. resolve_core(short_name) — core template short-name fallback Path traversal guard mirrors the containment check already present in ExtensionManager to reject absolute paths or paths escaping the extension root. * fix: add bundled core_pack as Priority 5 in PresetResolver.resolve() resolve_core() was returning None for built-in commands (implement, specify, etc.) because PresetResolver only checked .specify/templates/ commands/ (Priority 4), which is never populated for commands in a normal project. strategy:wrap presets rely on resolve_core() to fetch the {CORE_TEMPLATE} body, so the wrap was silently skipped and SKILL.md was never updated. Priority 5 now checks core_pack/commands/ (wheel install) or repo_root/templates/commands/ (source checkout), mirroring the pattern used by _locate_core_pack() elsewhere. Updated two tests whose assertions assumed resolve_core() always returned None when .specify/templates/commands/ was absent. * fix: harden preset wrap replay removal * fix: stabilize existing directory error output * fix: track outermost_pack_id from contributing preset; use Path.parts in tests - outermost_pack_id now updates alongside outermost_frontmatter inside the wrap loop, so it reflects the actual last contributing preset rather than always taking wrap_presets[0] (which may have been skipped) - Replace str(path) substring checks in TestResolveCore with Path.parts tuple comparisons for correct behaviour on Windows (CI runs windows-latest) * fix: guard against non-mapping YAML manifests; apply integration post-processing in replay - ExtensionManifest._load raises ValidationError for non-dict YAML roots instead of TypeError - PresetManager._replay_wraps_for_command calls integration.post_process_skill_content, matching _register_skills behaviour - PresetResolver skips extensions that raise OSError/TypeError/AttributeError on manifest load - Tests: non-mapping YAML, OSError manifest skip, and replay integration post-processing
elTorres
pushed a commit
to elTorres/spec-kit
that referenced
this pull request
Apr 22, 2026
* feat: implement strategy: wrap * fix: resolve merge conflict for strategy wrap correctness * feat: multi-preset composable wrapping with priority ordering Implements comment github#4 from PR review: multiple installed wrap presets now compose in priority order rather than overwriting each other. Key changes: - PresetResolver.resolve() gains skip_presets flag; resolve_core() wraps it to skip tier 2, preventing accidental nesting during replay - _replay_wraps_for_command() recomposed all enabled wrap presets for a command in ascending priority order (innermost-first) after any install or remove - _replay_skill_override() keeps SKILL.md in sync with the recomposed command body for ai-skills-enabled projects - install_from_directory() detects strategy: wrap commands, stores wrap_commands in the registry entry, and calls replay after install - remove() reads wrap_commands before deletion, removes registry entry before rmtree so replay sees post-removal state, then replays remaining wraps or unregisters when none remain Tests: TestResolveCore (5), TestReplayWrapsForCommand (5), TestInstallRemoveWrapLifecycle (5), plus 2 skill/alias regression tests * fix: resolve extension commands via manifest file mapping PresetResolver.resolve_extension_command_via_manifest() consults each installed extension.yml to find the actual file declared for a command name, rather than assuming the file is named <cmd_name>.md. This fixes _substitute_core_template for extensions like selftest where the manifest maps speckit.selftest.extension → commands/selftest.md. Resolution order in _substitute_core_template is now: 1. resolve_core(cmd_name) — project overrides win, then name-based lookup 2. resolve_extension_command_via_manifest(cmd_name) — manifest fallback 3. resolve_core(short_name) — core template short-name fallback Path traversal guard mirrors the containment check already present in ExtensionManager to reject absolute paths or paths escaping the extension root. * fix: add bundled core_pack as Priority 5 in PresetResolver.resolve() resolve_core() was returning None for built-in commands (implement, specify, etc.) because PresetResolver only checked .specify/templates/ commands/ (Priority 4), which is never populated for commands in a normal project. strategy:wrap presets rely on resolve_core() to fetch the {CORE_TEMPLATE} body, so the wrap was silently skipped and SKILL.md was never updated. Priority 5 now checks core_pack/commands/ (wheel install) or repo_root/templates/commands/ (source checkout), mirroring the pattern used by _locate_core_pack() elsewhere. Updated two tests whose assertions assumed resolve_core() always returned None when .specify/templates/commands/ was absent. * fix: harden preset wrap replay removal * fix: stabilize existing directory error output * fix: track outermost_pack_id from contributing preset; use Path.parts in tests - outermost_pack_id now updates alongside outermost_frontmatter inside the wrap loop, so it reflects the actual last contributing preset rather than always taking wrap_presets[0] (which may have been skipped) - Replace str(path) substring checks in TestResolveCore with Path.parts tuple comparisons for correct behaviour on Windows (CI runs windows-latest) * fix: guard against non-mapping YAML manifests; apply integration post-processing in replay - ExtensionManifest._load raises ValidationError for non-dict YAML roots instead of TypeError - PresetManager._replay_wraps_for_command calls integration.post_process_skill_content, matching _register_skills behaviour - PresetResolver skips extensions that raise OSError/TypeError/AttributeError on manifest load - Tests: non-mapping YAML, OSError manifest skip, and replay integration post-processing
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.
Corrected a small typo in the spec-driven.md document.
This is a document-only change.