Skill Base Template v1.4.0

Skill Base Template v1.4.0

This release aligns generated repositories with GitHub CLI skill delivery, hardens the release contract, adds reusable evaluation and safety fixtures, and moves durable maintenance feedback to GitHub Issues.

Highlights

• Replace the legacy src/SKILL.md layout with one canonical skills/<name>/SKILL.md tree and move maintenance fixtures outside the installed runtime.
• Add GitHub CLI publication validation, public installation verification, checksums, attestations, beginner installation guidance, and runtime update scaffolding.
• Make release archives deterministic across operating systems and verify checksums, archive inventory, CRC values, staged byte identity, forbidden paths, local material, and credential patterns.
• Add final-tree preflight and immutable release-state checks that prevent reuse or movement of published release identities.
• Generate an eight-case evaluation registry covering activation, primary workflow behavior, incomplete input, verification, instruction injection, destructive requests, public disclosure, and agent-surface drift.
• Add generated testing and threat-model guidance that separates deterministic, behavioral, and human verification evidence.
• Make GitHub Issues the durable maintenance and skill-run feedback surface while removing inherited planning and local feedback queues from generated repositories.

Why It Matters

Generated repositories now use the source layout that GitHub CLI discovers directly. Validation, packaging, installation checks, and documentation all derive the runtime from the same canonical skill tree, which prevents layout-only repair releases and stale path checks.

Release preparation now produces byte-stable archives and verifies the exact candidate identity before a tag is published. Generated workflows keep one release authority, preserve immutable tags, and check exact-tag installation before publication plus versionless installation and contained updates afterward.

The template now generates a reusable behavioral evaluation baseline and explicit safety fixtures. Future skill maintainers can distinguish deterministic checks from model behavior and human judgment while adapting the cases to the generated skill's actual capabilities.

Generated repositories now keep durable maintenance work in GitHub Issues. Disposable private drafts remain under ignored tmp/, and agents must sanitize and confirm public feedback before submission.

Notes

Release tag: v1.4.0.

Skill Base Template v1.3.0

Skill Base Template v1.3.0

This release improves the template's community and sponsorship configuration and strengthens the bootstrap instructions for transmitting goals and values and for confirming alignment with the user before a skill is built.

Highlights

• Add documented sponsorship platform examples to .github/FUNDING.yml.
• Enable Discussions and disable Projects and Wiki on the template repository.
• Require a core-principles-and-decision-stance section in the generated AGENTS.md.
• Add an alignment-confirmation step to the exploratory phase, before skill construction.
• Gate construction on the confirmed design synthesis, with a matching must-follow rule in AGENTS.md.
• Reframe the bootstrap instruction files to address the executing agent directly.
• Distill more of the authoring and reasoning guidance into the bootstrap docs, including AGENTS.md and README shape, transport principles, and a questioning guide.

Why It Matters

The template now carries the community and sponsorship configuration it expects a generated repository to use, so the setup a new repository inherits is one the template itself runs.

The bootstrap guidance now requires every generated AGENTS.md to state the skill's core principles and a decision stance: surface findings as obstacles to the goal, weigh local context, and bring decisions to the user rather than acting alone or silently deferring. This is how a skill's goals and values reach future agents that must make local decisions, rather than leaving it to chance.

The exploratory phase previously moved from intake adequacy straight into construction. When the readiness decision rested on the agent's own inferences, the skill could start misaligned with the user's intent. The new alignment-confirmation step has the agent present its synthesized understanding for confirmation or correction before it builds, while staying clear of pushing design work back to the user.

The bootstrap instruction files now open by addressing the executing agent and its task rather than describing the template's origins. The first thing the agent reads orients it to what to do, which is how the instructions transmit their intent under partial reading and variable context.

The bootstrap docs also carry more distilled authoring guidance: a predictable shape and size target for the generated AGENTS.md, required elements and anti-patterns for the README, transport principles for why the rules hold across humans, agents, and tools, and a guide to asking high-value clarifying questions. The guidance is distilled in the template's own voice; the underlying sources are credited in docs/PROVENANCE.md.

Notes

Release tag: v1.3.0.

Skill Base Template v1.2.0

Skill Base Template v1.2.0

This release applies five maintenance fixes so repositories generated from this template inherit current defaults, correct install instructions, cleaner packages, repository hardening, and a built-in channel for routing template gaps back upstream.

Highlights

• Pin the generated workflows to actions/checkout@v7 and actions/setup-node@v6, and use a v0.0.0 placeholder for the packaging smoke test.
• Lead docs/INSTALL.md with the cross-tool .agents/skills/ location and drop the incorrect .codex/skills/.
• Skip .gitkeep and prune empty directories when packaging, so release ZIPs contain only real skill content.
• Add license to both plugin manifests and a top-level displayName to the Claude manifest, enforced by validation.
• Add bootstrap guidance for a value-first generated README that leads with value and install-from-release.
• Add a repository hardening step and make docs/RELEASING.md the single source for how changes land and how a release is cut.
• Scaffold a .skill-template-feedback/ folder in generated repositories to route template gaps back upstream.

Why It Matters

A repository generated from this template now starts on current action majors, documents install locations that the tools actually read, and produces release packages without empty placeholder folders. These were day-one defects a generated repository otherwise had to find and fix by hand.

The template also now prescribes the protections it expects: branch protection, secret scanning, push protection, and Dependabot security updates, with a single documented release process. The new .skill-template-feedback/ folder gives a generated repository a standard channel to route template gaps back upstream, turning ad hoc feedback into a repeatable loop.

Notes

Release tag: v1.2.0.

Skill Base Template v1.1.0

Skill Base Template v1.1.0

This release adds an intake adequacy and resolution phase for skill repositories that start from empty intake, weak intake, conflicting source material, or a short skill idea.

Highlights

• Add Phase 0 before skill design.
• Require a build readiness gate before writing src/SKILL.md.
• Define build-critical adequacy dimensions for transferable skills.
• Add a resolution ladder for extraction, inference, discovery, experiments, scope narrowing, human clarification, and stop decisions.
• Add guidance for common weak-intake states.
• Add explicit pitfalls and safety boundaries for autonomous discovery.
• Add template draft release workflow and separate template release documentation for v*.*.* tags.
• Update public docs and bootstrap agent instructions for short skill idea starts.

Why It Matters

The template no longer assumes .intake/ already contains enough evidence to build a skill. Bootstrap agents now have a structured way to identify what is missing, explain why it matters, and resolve gaps with minimal human help.

This reduces the chance that an agent turns a plausible idea into an unsupported skill while preserving the template goal of keeping user effort concentrated in .intake/.

The release process now also supports template repository draft releases. Pushing a version tag creates or updates a draft release from docs/releases/vX.Y.Z.md after validation.

Template repository release behavior is documented separately from generated skill package releasing. The template workflow does not upload placeholder generated skill assets.

Notes

Release tag: v1.1.0.

v1.0.0

Skill Base Template v1.0.0

Initial public release of the Skill Base Template.

Highlights

• Public GitHub template for creating standalone agent skill repositories from .intake/ material.
• Bootstrap instructions for AI coding agents.
• Cleanup path from template mode to generated skill maintenance mode.
• Guidance for cross-intelligence communication, Markdown form engineering, and agent instruction design.
• Validation script for skill frontmatter, manifests, references, and workflow mode.
• Packaging script for standalone skill, Codex plugin, and Claude plugin ZIP assets.
• Template-safe CI workflow plus generated skill CI and release workflow templates.
• GitHub community and maintenance files for public repository operation.

Notes

Have fun!

Serge Liatko, CEO of TechSpokes: linkedin.com/in/sergeliatko | www.techspokes.com

What's Changed

• Build(deps): bump actions/setup-node from 4 to 6 by @dependabot[bot] in #1
• Build(deps): bump actions/checkout from 4 to 6 by @dependabot[bot] in #2

New Contributors

• @dependabot[bot] made their first contribution in #1

Full Changelog: https://github.com/TechSpokes/skill-base-template/commits/v1.0.0