8Dionysus/aoa-session-progression-lift
.agents/skills/aoa-session-progression-lift/SKILL.md
Lift reviewed session evidence into a bounded multi-axis progression delta with explicit unlock hints, quest reflection cues, and no fake single-score authority. Use when a reviewed session produced meaningful mastery evidence and you need progression legibility without mutating source role profiles or routing authority. Do not use when there is no reviewed evidence, when the request wants one universal power number, or when progression language is being used as hidden policy.
$ install --global
skillsauthnpx skillsauth add 8Dionysus/aoa-skills aoa-session-progression-liftInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 1:06 PM88.0s1 file scanned
SKILL.md
- name:
- aoa-session-progression-lift
- description:
- Lift reviewed session evidence into a bounded multi-axis progression delta with explicit unlock hints, quest reflection cues, and no fake single-score authority. Use when a reviewed session produced meaningful mastery evidence and you need progression legibility without mutating source role profiles or routing authority. Do not use when there is no reviewed evidence, when the request wants one universal power number, or when progression language is being used as hidden policy.
- license:
- Apache-2.0
- compatibility:
- Designed for Codex or similar coding agents with repository file access and an interactive shell. Network access is optional and only needed when repository validation or referenced workflows require it.
- aoa_scope:
- core
- aoa_status:
- scaffold
- aoa_invocation_mode:
- explicit-only
- aoa_source_skill_path:
- skills/aoa-session-progression-lift/SKILL.md
- aoa_source_repo:
- 8Dionysus/aoa-skills
- aoa_technique_dependencies:
- AOA-T-0084,AOA-T-0085
- aoa_portable_profile:
- codex-facing-wave-3
aoa-session-progression-lift
Intent
Use this skill to author a PROGRESSION_DELTA from reviewed evidence.
This is not score inflation. It is an evidence-backed overlay that says what mastery axes moved, what should hold or reanchor, and what small unlock hints are now safer.
Trigger boundary
Use this skill when:
- a reviewed session generated meaningful mastery evidence
- the route needs progression legibility without mutating source role profiles
- quest or RPG reflection would help continuation
- the output needs to stay small, evidence-backed, and multi-axis
Do not use this skill when:
- there is no reviewed evidence
- the request wants one global power number
- progression is being used as hidden routing policy
- the route is trying to mint authority rights without evidence
Inputs
- reviewed session artifact or harvest packet
- named evidence refs
- relevant role or cohort context if known
- existing progression baseline if available
Outputs
PROGRESSION_DELTAwith axis movement, verdict, and optional unlock hints- optional automation-readiness hint when reviewed evidence supports it
- optional rank reflection note if evidence is strong enough
- quest hooks or chronicle stub when useful
- negative or cautionary evidence when a hold, reanchor, or downgrade is more honest than advance
- one
PROGRESSION_DELTA_RECEIPTusingreferences/stats-event-envelope.mdandreferences/progression-delta-receipt-schema.yaml - one
CORE_SKILL_APPLICATION_RECEIPTusingreferences/core-skill-application-receipt-schema.yaml
Procedure
- collect reviewed evidence refs
- assess movement qualitatively across
boundary_integrity,execution_reliability,change_legibility,review_sharpness,proof_discipline,provenance_hygiene, anddeep_readiness - emit a verdict: advance, hold, reanchor, or downgrade
- name small unlock hints only when evidence supports them
- keep any automation-readiness hint small, descriptive, and non-authoritative
- allow negative, zero, and cautionary movement
- map ability or feat hints only as reflection, not as ownership transfer
- emit one
PROGRESSION_DELTA_RECEIPTwhen the delta closes, keeping the receipt descriptive, evidence-linked, and smaller than the progression packet - when the finish path closes, emit one
CORE_SKILL_APPLICATION_RECEIPTthat points back to the bounded progression receipt and records one finished kernel-skill application
Contracts
- progression remains evidence-backed
- multi-axis only; no authoritative universal score
- rank labels are descriptive, not sovereign
- unlock hints must stay reviewable and small
- progression does not replace owner-layer truth or routing authority
- progression does not greenlight automation by itself
- progression receipts stay descriptive and append-only
- generic core receipts stay subordinate to the progression receipt and do not become progression authority
- receipt corrections use
supersedesrather than silent overwrite
Risks and anti-patterns
- inventing progress from mood
- using progression as policy
- granting authority without cited evidence
- flattening multi-axis growth into one number
- confusing quest flavor with durable proof
- treating progression hints as if they were approval or schedule rights
- treating a progression receipt as if receipt emission itself proved growth
Verification
- confirm all meaningful axis claims cite reviewed evidence
- confirm the verdict matches the evidence
- confirm zero or negative movement remains allowed
- confirm unlock hints are small and explicit
- confirm no universal score is introduced
- confirm any emitted receipt stays multi-axis, evidence-linked, and non-sovereign
- confirm any emitted
CORE_SKILL_APPLICATION_RECEIPTpoints to the progression detail receipt and stays finish-only
Technique traceability
Manifest-backed techniques:
- AOA-T-0084 from
8Dionysus/aoa-techniquesat5c6f0496edc3c2e74590baa35627c85fe58ef765using pathtechniques/agent-workflows/progression-evidence-lift/TECHNIQUE.mdand sections: Intent, Inputs, Outputs, Contracts, Validation - AOA-T-0085 from
8Dionysus/aoa-techniquesat5c6f0496edc3c2e74590baa35627c85fe58ef765using pathtechniques/agent-workflows/multi-axis-quest-overlay/TECHNIQUE.mdand sections: Outputs, Risks, Validation
Adaptation points
Project overlays may add:
- local axis notes
- role-affinity hints
- local unlock classes
Related Skills
8Dionysus/aoa-knowledge-stewardship
development
VerifiedTrustedCommunity
Sanitize private technical material into a public-safe owner-bounded derivative, or resolve authority among authored, generated, runtime, and installed sources. Use for governed incidents, logs, configs, diagnostics, or conflicting source roles. Do not use for ordinary editing, memo/session work, direct publication, or durable-memory authority.
4SKILL.mdUpdated Jul 16, 2026
8Dionysus/aoa-session-recovery
tools
VerifiedTrustedCommunity
Diagnose a reviewed recurring session/workflow failure, or carry one bounded owner repair through checkpoint, rollback, and real health verification. Use for reviewed contamination, drift, repeated route/tool failure, or an established diagnosis ready for repair. Do not use on live evidence, for vague self-improvement, or to call a proposed or merely executed change verified.
4SKILL.mdUpdated Jul 16, 2026
8Dionysus/aoa-session-harvest
tools
VerifiedTrustedCommunity
Use only when a literal ref to a closed/reviewed session packet is supplied, to extract, classify, propose promotion or branching, or identify an automation opportunity. Missing, live, or unreviewed evidence must fail closed without inventing a ref. Natural closeout preservation belongs to aoa-memo-writeback. Do not use for generic summaries, progression, direct owner writes, scheduling, mutation, or telemetry authority.
4SKILL.mdUpdated Jul 16, 2026
8Dionysus/aoa-verification
testing
VerifiedTrustedCommunity
Turn one stable technical truth into bounded evidence through contract, coverage-audit, or property mode. Use to define a named consumer seam, audit what existing checks really constrain, or express a broad invariant after manual cases establish meaning. Compose with aoa-eval when an evaluation surface must first be found or applied. Do not use for undefined behavior, generic test plans, or green checks as whole-system proof.
4SKILL.mdUpdated Jul 16, 2026